Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7742. Min Act: -0.1700
Data Index: 2759663 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7656. Min Act: -0.1700
Data Index: 7992854 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7483. Min Act: -0.1700
Data Index: 4105507 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7397. Min Act: -0.1700
Data Index: 7720460 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7483. Min Act: -0.1700
Data Index: 2331027 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7483. Min Act: -0.1700
Data Index: 8228313 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7397. Min Act: -0.1700
Data Index: 3827443 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7397. Min Act: -0.1700
Data Index: 8185467 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7310. Min Act: -0.1700
Data Index: 790919 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7397. Min Act: -0.1700
Data Index: 7649566 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7310. Min Act: -0.1700
Data Index: 3366221 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7397. Min Act: -0.1700
Data Index: 2761275 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7310. Min Act: -0.1700
Data Index: 894199 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7224. Min Act: -0.1700
Data Index: 671724 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7137. Min Act: -0.1700
Data Index: 1283679 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7137. Min Act: -0.1700
Data Index: 3904171 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7137. Min Act: -0.1700
Data Index: 340236 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7137. Min Act: -0.1700
Data Index: 1818270 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7050. Min Act: -0.1700
Data Index: 2475753 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7742. Min Range: -1.7742
Max Act: 1.7050. Min Act: -0.1700
Data Index: 938217 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19