Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4042. Min Range: -7.4042
Max Act: 7.4042. Min Act: -0.1700
Data Index: 8534703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4042. Min Range: -7.4042
Max Act: 7.2480. Min Act: -0.1700
Data Index: 8484161 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.9980. Min Act: -0.1700
Data Index: 1613539 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.9042. Min Act: -0.1700
Data Index: 8619848 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.8730. Min Act: -0.1700
Data Index: 3275547 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.8417. Min Act: -0.1700
Data Index: 3803820 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.8417. Min Act: -0.1700
Data Index: 359008 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.8105. Min Act: -0.1700
Data Index: 762141 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.7480. Min Act: -0.1700
Data Index: 1957962 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.7480. Min Act: -0.1700
Data Index: 6547978 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.7167. Min Act: -0.1700
Data Index: 6003124 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6855. Min Act: -0.1700
Data Index: 3589345 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6855. Min Act: -0.1700
Data Index: 2919651 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6855. Min Act: -0.1700
Data Index: 7241443 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6855. Min Act: -0.1700
Data Index: 8506428 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6855. Min Act: -0.1700
Data Index: 2179781 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6542. Min Act: -0.1700
Data Index: 2598266 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6542. Min Act: -0.1700
Data Index: 8654783 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6542. Min Act: -0.1700
Data Index: 769760 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4042. Min Range: -7.4042
Max Act: 6.6230. Min Act: -0.1700
Data Index: 5293936 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19