Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1924 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.8043. Min Act: -0.1700
Data Index: 1125728 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.7725. Min Act: -0.1700
Data Index: 3854679 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.7565. Min Act: -0.1700
Data Index: 7317323 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.7405. Min Act: -0.1700
Data Index: 6115766 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6926. Min Act: -0.1700
Data Index: 3670198 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.7086. Min Act: -0.1700
Data Index: 1297316 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6926. Min Act: -0.1700
Data Index: 8689205 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.7246. Min Act: -0.1700
Data Index: 8641589 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6926. Min Act: -0.1700
Data Index: 308308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6605. Min Act: -0.1700
Data Index: 8658135 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6284. Min Act: -0.1700
Data Index: 5788051 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6605. Min Act: -0.1700
Data Index: 8405465 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6445. Min Act: -0.1700
Data Index: 3145510 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6445. Min Act: -0.1700
Data Index: 3206055 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6284. Min Act: -0.1700
Data Index: 1927527 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6284. Min Act: -0.1700
Data Index: 2360542 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6123. Min Act: -0.1700
Data Index: 746200 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6123. Min Act: -0.1700
Data Index: 3021949 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.6123. Min Act: -0.1700
Data Index: 6719800 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8043. Min Range: -2.8043
Max Act: 2.5801. Min Act: -0.1700
Data Index: 7980277 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19