Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.9318. Min Range: -10.9318
Max Act: 10.9318. Min Act: -0.1700
Data Index: 4363818 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9318. Min Range: -10.9318
Max Act: 10.4943. Min Act: -0.1700
Data Index: 3085867 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9318. Min Range: -10.9318
Max Act: 10.4943. Min Act: -0.1700
Data Index: 6265042 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9318. Min Range: -10.9318
Max Act: 10.3068. Min Act: -0.1700
Data Index: 8252695 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9318. Min Range: -10.9318
Max Act: 10.1818. Min Act: -0.1700
Data Index: 681921 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9318. Min Range: -10.9318
Max Act: 10.1193. Min Act: -0.1700
Data Index: 92539 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9318. Min Range: -10.9318
Max Act: 10.1193. Min Act: -0.1700
Data Index: 8644455 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.9943. Min Act: -0.1700
Data Index: 8687895 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.9318. Min Act: -0.1700
Data Index: 8582199 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.9943. Min Act: -0.1700
Data Index: 3815523 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.9318. Min Act: -0.1700
Data Index: 2159110 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.9318. Min Act: -0.1700
Data Index: 8787028 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.6818. Min Act: -0.1700
Data Index: 3916065 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.7443. Min Act: -0.1700
Data Index: 3915658 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.7443. Min Act: -0.1700
Data Index: 8780474 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.7443. Min Act: -0.1700
Data Index: 4376252 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.7443. Min Act: -0.1700
Data Index: 2552118 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.7443. Min Act: -0.1700
Data Index: 2612592 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.6818. Min Act: -0.1700
Data Index: 849554 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9318. Min Range: -10.9318
Max Act: 9.6818. Min Act: -0.1700
Data Index: 61892 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19