Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5718 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.9520. Min Act: -0.1700
Data Index: 6808981 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.8582. Min Act: -0.1700
Data Index: 2203444 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.7957. Min Act: -0.1700
Data Index: 6103459 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.7645. Min Act: -0.1700
Data Index: 2515731 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.7645. Min Act: -0.1700
Data Index: 1960306 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.7645. Min Act: -0.1700
Data Index: 7734654 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.7332. Min Act: -0.1700
Data Index: 4123405 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.7020. Min Act: -0.1700
Data Index: 7737586 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6707. Min Act: -0.1700
Data Index: 3543747 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6707. Min Act: -0.1700
Data Index: 2239357 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6707. Min Act: -0.1700
Data Index: 2044689 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6532250 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6373061 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6707. Min Act: -0.1700
Data Index: 5504797 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7248584 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6082. Min Act: -0.1700
Data Index: 3711234 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6082. Min Act: -0.1700
Data Index: 2068758 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.6082. Min Act: -0.1700
Data Index: 5600405 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.5770. Min Act: -0.1700
Data Index: 3953751 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9520. Min Range: -5.9520
Max Act: 5.5770. Min Act: -0.1700
Data Index: 7737578 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19