Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 212 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.3129. Min Act: -0.1700
Data Index: 4434302 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.2800. Min Act: -0.1700
Data Index: 1206752 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.2635. Min Act: -0.1700
Data Index: 1206753 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.2304. Min Act: -0.1700
Data Index: 5729736 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.2304. Min Act: -0.1700
Data Index: 602824 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.2139. Min Act: -0.1700
Data Index: 6228302 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.2304. Min Act: -0.1700
Data Index: 7982330 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.2139. Min Act: -0.1700
Data Index: 2148716 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1973. Min Act: -0.1700
Data Index: 5202894 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1973. Min Act: -0.1700
Data Index: 666564 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1973. Min Act: -0.1700
Data Index: 4507241 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1973. Min Act: -0.1700
Data Index: 2923137 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1807. Min Act: -0.1700
Data Index: 5037350 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1807. Min Act: -0.1700
Data Index: 3410700 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1807. Min Act: -0.1700
Data Index: 3455166 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1807. Min Act: -0.1700
Data Index: 7392084 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1807. Min Act: -0.1700
Data Index: 481439 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1807. Min Act: -0.1700
Data Index: 3909559 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1807. Min Act: -0.1700
Data Index: 5720674 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3129. Min Range: -2.3129
Max Act: 2.1640. Min Act: -0.1700
Data Index: 874447 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19