Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1915 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.9199. Min Act: -0.1700
Data Index: 6210813 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.8261. Min Act: -0.1700
Data Index: 5857801 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7635. Min Act: -0.1700
Data Index: 617402 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7635. Min Act: -0.1700
Data Index: 8359726 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7166. Min Act: -0.1700
Data Index: 6667095 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7323. Min Act: -0.1700
Data Index: 4619896 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7010. Min Act: -0.1700
Data Index: 759001 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7323. Min Act: -0.1700
Data Index: 6809333 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7010. Min Act: -0.1700
Data Index: 2845309 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7010. Min Act: -0.1700
Data Index: 5818121 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6853. Min Act: -0.1700
Data Index: 7940168 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6853. Min Act: -0.1700
Data Index: 1145499 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6853. Min Act: -0.1700
Data Index: 6747433 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6853. Min Act: -0.1700
Data Index: 6115282 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6384. Min Act: -0.1700
Data Index: 3309282 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6227. Min Act: -0.1700
Data Index: 4043020 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6227. Min Act: -0.1700
Data Index: 327503 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6384. Min Act: -0.1700
Data Index: 3627837 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6227. Min Act: -0.1700
Data Index: 4081952 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6227. Min Act: -0.1700
Data Index: 564283 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19