Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0971. Min Range: -9.0971
Max Act: 9.0971. Min Act: -0.1700
Data Index: 1753137 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0971. Min Range: -9.0971
Max Act: 9.0346. Min Act: -0.1700
Data Index: 7651592 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0971. Min Range: -9.0971
Max Act: 9.0346. Min Act: -0.1700
Data Index: 1315630 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.9721. Min Act: -0.1700
Data Index: 5186511 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.9096. Min Act: -0.1700
Data Index: 7595998 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.9096. Min Act: -0.1700
Data Index: 6223442 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.9096. Min Act: -0.1700
Data Index: 2340956 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.9096. Min Act: -0.1700
Data Index: 5796399 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7846. Min Act: -0.1700
Data Index: 7570689 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.8471. Min Act: -0.1700
Data Index: 966267 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7846. Min Act: -0.1700
Data Index: 824939 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7846. Min Act: -0.1700
Data Index: 7409397 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7846. Min Act: -0.1700
Data Index: 5776942 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7846. Min Act: -0.1700
Data Index: 1780573 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7221. Min Act: -0.1700
Data Index: 103461 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7221. Min Act: -0.1700
Data Index: 5960710 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7221. Min Act: -0.1700
Data Index: 1602251 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7221. Min Act: -0.1700
Data Index: 634314 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7221. Min Act: -0.1700
Data Index: 3650188 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0971. Min Range: -9.0971
Max Act: 8.7221. Min Act: -0.1700
Data Index: 3386366 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19