Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1676 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 10.0438. Min Range: -10.0438
Max Act: 10.0438. Min Act: -0.1700
Data Index: 1442021 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.7313. Min Act: -0.1700
Data Index: 3676419 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.6688. Min Act: -0.1700
Data Index: 999295 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.4188. Min Act: -0.1700
Data Index: 7152047 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.2938. Min Act: -0.1700
Data Index: 3676420 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.2938. Min Act: -0.1700
Data Index: 4462690 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.1688. Min Act: -0.1700
Data Index: 7059812 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.1063. Min Act: -0.1700
Data Index: 999302 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.1063. Min Act: -0.1700
Data Index: 6726565 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 2321407 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.1063. Min Act: -0.1700
Data Index: 4462673 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 6201572 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 7059821 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0438. Min Range: -10.0438
Max Act: 9.0438. Min Act: -0.1700
Data Index: 7029720 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0438. Min Range: -10.0438
Max Act: 8.9813. Min Act: -0.1700
Data Index: 2317264 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0438. Min Range: -10.0438
Max Act: 8.9188. Min Act: -0.1700
Data Index: 7563655 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0438. Min Range: -10.0438
Max Act: 8.9813. Min Act: -0.1700
Data Index: 4890556 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0438. Min Range: -10.0438
Max Act: 8.9813. Min Act: -0.1700
Data Index: 4462703 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0438. Min Range: -10.0438
Max Act: 8.9813. Min Act: -0.1700
Data Index: 6837353 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0438. Min Range: -10.0438
Max Act: 8.9188. Min Act: -0.1700
Data Index: 999281 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19