Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.4290. Min Act: -0.1700
Data Index: 4229368 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.3506. Min Act: -0.1700
Data Index: 7151305 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.3035. Min Act: -0.1700
Data Index: 1473624 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.3035. Min Act: -0.1700
Data Index: 7315790 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.2407. Min Act: -0.1700
Data Index: 1292692 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.2092. Min Act: -0.1700
Data Index: 7302226 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.2092. Min Act: -0.1700
Data Index: 3618645 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.2092. Min Act: -0.1700
Data Index: 3222984 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1935. Min Act: -0.1700
Data Index: 3308184 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1778. Min Act: -0.1700
Data Index: 559972 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1935. Min Act: -0.1700
Data Index: 2909531 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1935. Min Act: -0.1700
Data Index: 5298856 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1778. Min Act: -0.1700
Data Index: 1893690 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1620. Min Act: -0.1700
Data Index: 8641382 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1463. Min Act: -0.1700
Data Index: 856224 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1463. Min Act: -0.1700
Data Index: 4916887 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1463. Min Act: -0.1700
Data Index: 3089986 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1463. Min Act: -0.1700
Data Index: 2925589 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1305. Min Act: -0.1700
Data Index: 6264610 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4290. Min Range: -3.4290
Max Act: 3.1148. Min Act: -0.1700
Data Index: 3223059 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19