Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3595 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0077. Min Range: -9.0077
Max Act: 9.0077. Min Act: -0.1700
Data Index: 6601348 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0077. Min Range: -9.0077
Max Act: 8.5077. Min Act: -0.1700
Data Index: 6450943 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0077. Min Range: -9.0077
Max Act: 8.5077. Min Act: -0.1700
Data Index: 231494 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0077. Min Range: -9.0077
Max Act: 8.3827. Min Act: -0.1700
Data Index: 231493 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0077. Min Range: -9.0077
Max Act: 8.2577. Min Act: -0.1697
Data Index: 4200380 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0077. Min Range: -9.0077
Max Act: 8.0702. Min Act: -0.1700
Data Index: 735937 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0077. Min Range: -9.0077
Max Act: 8.0702. Min Act: -0.1695
Data Index: 5223497 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0077. Min Range: -9.0077
Max Act: 8.0390. Min Act: -0.1700
Data Index: 6502025 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.9765. Min Act: -0.1700
Data Index: 3494443 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.9452. Min Act: -0.1700
Data Index: 5233670 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.8827. Min Act: -0.1700
Data Index: 6261731 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.8827. Min Act: -0.1700
Data Index: 4527768 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.8202. Min Act: -0.1700
Data Index: 7527244 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.7890. Min Act: -0.1700
Data Index: 7828729 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.7577. Min Act: -0.1700
Data Index: 3994665 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.7265. Min Act: -0.1700
Data Index: 3615720 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.7265. Min Act: -0.1700
Data Index: 384129 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.6952. Min Act: -0.1700
Data Index: 4665658 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.6327. Min Act: -0.1700
Data Index: 4527761 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0077. Min Range: -9.0077
Max Act: 7.6327. Min Act: -0.1700
Data Index: 4666877 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19