Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.9092. Min Act: -0.1700
Data Index: 2241672 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.9092. Min Act: -0.1700
Data Index: 5887282 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.8779. Min Act: -0.1700
Data Index: 804997 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.8467. Min Act: -0.1700
Data Index: 7359180 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.8154. Min Act: -0.1700
Data Index: 684864 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.8154. Min Act: -0.1700
Data Index: 326321 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.8154. Min Act: -0.1700
Data Index: 6824382 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.8154. Min Act: -0.1700
Data Index: 6813440 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7841. Min Act: -0.1700
Data Index: 8245375 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7841. Min Act: -0.1700
Data Index: 6474281 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7841. Min Act: -0.1700
Data Index: 3079124 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7841. Min Act: -0.1700
Data Index: 985595 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7841. Min Act: -0.1700
Data Index: 1427711 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7841. Min Act: -0.1700
Data Index: 38490 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7841. Min Act: -0.1700
Data Index: 166444 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7216. Min Act: -0.1700
Data Index: 7671483 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7529. Min Act: -0.1700
Data Index: 2978358 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7529. Min Act: -0.1700
Data Index: 2711112 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7529. Min Act: -0.1700
Data Index: 1670072 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9092. Min Range: -3.9092
Max Act: 3.7529. Min Act: -0.1700
Data Index: 10106 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19