Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 899 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 16.3107. Min Range: -16.3107
Max Act: 16.3107. Min Act: -0.1687
Data Index: 6006884 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.3107. Min Range: -16.3107
Max Act: 16.1857. Min Act: -0.1700
Data Index: 7331497 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.9357. Min Act: -0.1681
Data Index: 4718294 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.3107. Min Range: -16.3107
Max Act: 16.0607. Min Act: -0.1698
Data Index: 630067 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.9357. Min Act: -0.1700
Data Index: 4983671 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.9357. Min Act: -0.1700
Data Index: 1059613 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.8107. Min Act: -0.1692
Data Index: 410543 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.8107. Min Act: -0.1699
Data Index: 6822298 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.8107. Min Act: -0.1700
Data Index: 4381516 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.8107. Min Act: -0.1698
Data Index: 4141218 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.6857. Min Act: -0.1681
Data Index: 6249885 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.8107. Min Act: -0.1692
Data Index: 4583385 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.6857. Min Act: -0.1700
Data Index: 5924285 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.6857. Min Act: -0.1698
Data Index: 5812330 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.6857. Min Act: -0.1700
Data Index: 7712960 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.6857. Min Act: -0.1700
Data Index: 3755744 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.6857. Min Act: -0.1699
Data Index: 450263 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.5607. Min Act: -0.1700
Data Index: 5924286 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.5607. Min Act: -0.1700
Data Index: 4668171 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.3107. Min Range: -16.3107
Max Act: 15.5607. Min Act: -0.1693
Data Index: 6181547 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19