Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.7744. Min Act: -0.1700
Data Index: 7016922 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.7119. Min Act: -0.1700
Data Index: 21020 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.6807. Min Act: -0.1700
Data Index: 4441977 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.6182. Min Act: -0.1700
Data Index: 7412396 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5869. Min Act: -0.1700
Data Index: 4840197 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5557. Min Act: -0.1700
Data Index: 1900979 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5869. Min Act: -0.1700
Data Index: 6997428 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5869. Min Act: -0.1700
Data Index: 8127679 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7870903 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7030361 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7854591 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.4932. Min Act: -0.1700
Data Index: 7776508 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5244. Min Act: -0.1700
Data Index: 6139671 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.5244. Min Act: -0.1700
Data Index: 8395453 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.4932. Min Act: -0.1700
Data Index: 8305810 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.4932. Min Act: -0.1700
Data Index: 1719868 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.4619. Min Act: -0.1700
Data Index: 2096656 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.4307. Min Act: -0.1700
Data Index: 7412395 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.4619. Min Act: -0.1700
Data Index: 7472670 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7744. Min Range: -5.7744
Max Act: 5.4307. Min Act: -0.1700
Data Index: 5431004 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19