Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.2398. Min Act: -0.1700
Data Index: 8344335 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.1461. Min Act: -0.1700
Data Index: 4186789 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.1461. Min Act: -0.1700
Data Index: 7403562 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.0211. Min Act: -0.1700
Data Index: 7842203 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2398. Min Range: -6.2398
Max Act: 6.0523. Min Act: -0.1700
Data Index: 7696179 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9898. Min Act: -0.1700
Data Index: 823808 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9586. Min Act: -0.1700
Data Index: 4125143 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9273. Min Act: -0.1700
Data Index: 1628856 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9273. Min Act: -0.1700
Data Index: 5158606 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.9273. Min Act: -0.1700
Data Index: 8733127 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8961. Min Act: -0.1700
Data Index: 7343683 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8961. Min Act: -0.1700
Data Index: 5790279 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8648. Min Act: -0.1700
Data Index: 2565868 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8648. Min Act: -0.1700
Data Index: 945414 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8336. Min Act: -0.1700
Data Index: 924107 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8336. Min Act: -0.1700
Data Index: 2761451 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8336. Min Act: -0.1700
Data Index: 7843782 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8336. Min Act: -0.1700
Data Index: 2067184 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8023. Min Act: -0.1700
Data Index: 2976364 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2398. Min Range: -6.2398
Max Act: 5.8023. Min Act: -0.1700
Data Index: 724066 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19