Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.8285. Min Act: -0.1700
Data Index: 4162362 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.8285. Min Act: -0.1700
Data Index: 8675727 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.8199. Min Act: -0.1700
Data Index: 8088948 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.8199. Min Act: -0.1699
Data Index: 3325728 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.8199. Min Act: -0.1700
Data Index: 1174631 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.8113. Min Act: -0.1700
Data Index: 747212 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7941. Min Act: -0.1700
Data Index: 2889582 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7855. Min Act: -0.1700
Data Index: 8375524 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7855. Min Act: -0.1700
Data Index: 500261 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7855. Min Act: -0.1700
Data Index: 8490128 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7855. Min Act: -0.1699
Data Index: 6858134 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7769. Min Act: -0.1700
Data Index: 4894917 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7855. Min Act: -0.1700
Data Index: 111518 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7596. Min Act: -0.1700
Data Index: 8580183 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7683. Min Act: -0.1700
Data Index: 4649507 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7596. Min Act: -0.1700
Data Index: 7498426 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7596. Min Act: -0.1700
Data Index: 8432791 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7596. Min Act: -0.1695
Data Index: 2027806 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7596. Min Act: -0.1680
Data Index: 5833485 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8285. Min Range: -1.8285
Max Act: 1.7510. Min Act: -0.1697
Data Index: 2925111 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19