Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2757. Min Range: -6.2757
Max Act: 6.2757. Min Act: -0.1700
Data Index: 924960 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2757. Min Range: -6.2757
Max Act: 6.0569. Min Act: -0.1700
Data Index: 2415866 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9944. Min Act: -0.1700
Data Index: 4583827 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2757. Min Range: -6.2757
Max Act: 6.0569. Min Act: -0.1700
Data Index: 8344206 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9944. Min Act: -0.1700
Data Index: 3193195 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1798691 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9319. Min Act: -0.1700
Data Index: 5747299 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9319. Min Act: -0.1700
Data Index: 6018997 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9007. Min Act: -0.1700
Data Index: 4047498 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9007. Min Act: -0.1700
Data Index: 7837567 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.9007. Min Act: -0.1700
Data Index: 2083535 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8694. Min Act: -0.1700
Data Index: 50753 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8382. Min Act: -0.1700
Data Index: 4113128 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8694. Min Act: -0.1700
Data Index: 2461534 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8382. Min Act: -0.1700
Data Index: 4746521 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8382. Min Act: -0.1700
Data Index: 3517337 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8382. Min Act: -0.1700
Data Index: 3256255 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8382. Min Act: -0.1700
Data Index: 5867258 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8382. Min Act: -0.1700
Data Index: 3459433 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2757. Min Range: -6.2757
Max Act: 5.8382. Min Act: -0.1700
Data Index: 2076770 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19