Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.3520. Min Act: -0.1700
Data Index: 806501 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.2895. Min Act: -0.1700
Data Index: 1579720 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.2895. Min Act: -0.1700
Data Index: 1208146 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.2895. Min Act: -0.1700
Data Index: 8524962 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.1645. Min Act: -0.1700
Data Index: 1208147 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.1020. Min Act: -0.1700
Data Index: 1579721 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.1645. Min Act: -0.1700
Data Index: 2717859 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3520. Min Range: -9.3520
Max Act: 9.0395. Min Act: -0.1700
Data Index: 2717858 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.9770. Min Act: -0.1700
Data Index: 6539734 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.9145. Min Act: -0.1700
Data Index: 5288965 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.8520. Min Act: -0.1700
Data Index: 368873 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.6645. Min Act: -0.1700
Data Index: 8632745 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.7270. Min Act: -0.1700
Data Index: 928910 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.6020. Min Act: -0.1700
Data Index: 6321860 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.5395. Min Act: -0.1700
Data Index: 6726166 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.4770. Min Act: -0.1700
Data Index: 1010433 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.6020. Min Act: -0.1700
Data Index: 5258075 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.4145. Min Act: -0.1700
Data Index: 4554064 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.4145. Min Act: -0.1700
Data Index: 4485754 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3520. Min Range: -9.3520
Max Act: 8.3520. Min Act: -0.1700
Data Index: 5516330 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19