Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4322 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.1130. Min Act: -0.1700
Data Index: 1472862 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0795. Min Act: -0.1700
Data Index: 4537913 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0627. Min Act: -0.1700
Data Index: 7255789 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0627. Min Act: -0.1700
Data Index: 5996435 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0627. Min Act: -0.1699
Data Index: 5259560 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0627. Min Act: -0.1700
Data Index: 4918403 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0459. Min Act: -0.1700
Data Index: 7228438 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0290. Min Act: -0.1700
Data Index: 5300854 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0459. Min Act: -0.1700
Data Index: 6875838 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0459. Min Act: -0.1700
Data Index: 1021990 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0459. Min Act: -0.1700
Data Index: 7658628 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0459. Min Act: -0.1700
Data Index: 6365817 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0290. Min Act: -0.1700
Data Index: 487434 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0290. Min Act: -0.1700
Data Index: 942411 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0290. Min Act: -0.1700
Data Index: 5057549 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0290. Min Act: -0.1700
Data Index: 3255193 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0290. Min Act: -0.1700
Data Index: 8733154 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0122. Min Act: -0.1700
Data Index: 6091069 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0290. Min Act: -0.1700
Data Index: 5931412 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1130. Min Range: -2.1130
Max Act: 2.0122. Min Act: -0.1700
Data Index: 935026 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19