Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2136 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3863. Min Range: -6.3863
Max Act: 6.3863. Min Act: -0.1700
Data Index: 1645395 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3863. Min Range: -6.3863
Max Act: 6.0425. Min Act: -0.1700
Data Index: 7385608 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3863. Min Range: -6.3863
Max Act: 6.0113. Min Act: -0.1700
Data Index: 2670672 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.9488. Min Act: -0.1700
Data Index: 1867594 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.9800. Min Act: -0.1700
Data Index: 8550903 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8863. Min Act: -0.1700
Data Index: 6454210 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.9175. Min Act: -0.1700
Data Index: 6621969 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.9175. Min Act: -0.1700
Data Index: 473421 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8863. Min Act: -0.1700
Data Index: 7857172 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8863. Min Act: -0.1700
Data Index: 7973440 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8863. Min Act: -0.1700
Data Index: 4134580 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8238. Min Act: -0.1700
Data Index: 8245206 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8550. Min Act: -0.1700
Data Index: 3927429 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.7925. Min Act: -0.1700
Data Index: 5954080 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8238. Min Act: -0.1700
Data Index: 6258248 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8238. Min Act: -0.1700
Data Index: 4434892 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.7925. Min Act: -0.1700
Data Index: 7721189 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.7925. Min Act: -0.1700
Data Index: 1628508 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.8238. Min Act: -0.1700
Data Index: 7731480 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3863. Min Range: -6.3863
Max Act: 5.7613. Min Act: -0.1700
Data Index: 7823575 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19