Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5821 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.4815. Min Act: -0.1700
Data Index: 5126017 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.4503. Min Act: -0.1700
Data Index: 6843258 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.4190. Min Act: -0.1700
Data Index: 7853992 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.3878. Min Act: -0.1700
Data Index: 690748 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.3878. Min Act: -0.1700
Data Index: 4975438 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.3253. Min Act: -0.1700
Data Index: 1475307 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.3565. Min Act: -0.1700
Data Index: 362635 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.3253. Min Act: -0.1700
Data Index: 1570369 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2628. Min Act: -0.1700
Data Index: 2761359 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2940. Min Act: -0.1700
Data Index: 1621874 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2940. Min Act: -0.1700
Data Index: 8487670 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2940. Min Act: -0.1700
Data Index: 7696135 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2628. Min Act: -0.1700
Data Index: 6903531 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2628. Min Act: -0.1700
Data Index: 5616733 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2628. Min Act: -0.1700
Data Index: 8513051 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2315. Min Act: -0.1700
Data Index: 1460422 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2315. Min Act: -0.1700
Data Index: 2312581 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2315. Min Act: -0.1700
Data Index: 5854803 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2003. Min Act: -0.1700
Data Index: 4663353 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4815. Min Range: -5.4815
Max Act: 5.2003. Min Act: -0.1700
Data Index: 2602204 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19