Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.7614. Min Act: -0.1700
Data Index: 4519661 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.7927. Min Act: -0.1700
Data Index: 6641494 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.6989. Min Act: -0.1700
Data Index: 2567021 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.6052. Min Act: -0.1700
Data Index: 1724738 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.5114. Min Act: -0.1700
Data Index: 6193964 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4489. Min Act: -0.1700
Data Index: 3032697 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4489. Min Act: -0.1700
Data Index: 2798407 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4489. Min Act: -0.1700
Data Index: 8671200 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.3864. Min Act: -0.1700
Data Index: 2178717 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4489. Min Act: -0.1700
Data Index: 4493278 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4802. Min Act: -0.1700
Data Index: 6064886 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4177. Min Act: -0.1700
Data Index: 6335464 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4177. Min Act: -0.1700
Data Index: 5612114 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.4177. Min Act: -0.1700
Data Index: 4476380 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.3552. Min Act: -0.1700
Data Index: 1387904 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.3864. Min Act: -0.1700
Data Index: 1408667 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.3552. Min Act: -0.1700
Data Index: 7867706 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.3239. Min Act: -0.1700
Data Index: 8507182 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.3552. Min Act: -0.1700
Data Index: 4284273 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7927. Min Range: -6.7927
Max Act: 6.3864. Min Act: -0.1700
Data Index: 3081257 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19