Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2790 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.5223. Min Act: -0.1700
Data Index: 2994548 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.4285. Min Act: -0.1700
Data Index: 6265626 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.3660. Min Act: -0.1700
Data Index: 7909877 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.3348. Min Act: -0.1700
Data Index: 1783270 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.2723. Min Act: -0.1700
Data Index: 6386147 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.2723. Min Act: -0.1700
Data Index: 5127616 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.2098. Min Act: -0.1700
Data Index: 6961613 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.0535. Min Act: -0.1700
Data Index: 922359 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.1160. Min Act: -0.1700
Data Index: 6627543 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.1160. Min Act: -0.1700
Data Index: 307767 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.1160. Min Act: -0.1700
Data Index: 8059934 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.0848. Min Act: -0.1700
Data Index: 780435 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.0848. Min Act: -0.1700
Data Index: 3215527 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.0223. Min Act: -0.1700
Data Index: 3124952 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.0535. Min Act: -0.1700
Data Index: 2802655 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5223. Min Range: -6.5223
Max Act: 6.0223. Min Act: -0.1700
Data Index: 6650931 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5223. Min Range: -6.5223
Max Act: 5.9598. Min Act: -0.1700
Data Index: 7534280 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5223. Min Range: -6.5223
Max Act: 5.9285. Min Act: -0.1700
Data Index: 4319401 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5223. Min Range: -6.5223
Max Act: 5.9598. Min Act: -0.1700
Data Index: 4618914 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5223. Min Range: -6.5223
Max Act: 5.9285. Min Act: -0.1700
Data Index: 5828323 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19