Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.4967. Min Act: -0.1700
Data Index: 2514552 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.4654. Min Act: -0.1700
Data Index: 55028 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.4029. Min Act: -0.1700
Data Index: 767430 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.3404. Min Act: -0.1700
Data Index: 8665848 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.3717. Min Act: -0.1700
Data Index: 7010 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2779. Min Act: -0.1700
Data Index: 6588053 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2467. Min Act: -0.1700
Data Index: 5356147 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2154. Min Act: -0.1700
Data Index: 796951 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2467. Min Act: -0.1700
Data Index: 4157242 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2467. Min Act: -0.1700
Data Index: 4492071 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2779. Min Act: -0.1700
Data Index: 6956282 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2467. Min Act: -0.1700
Data Index: 6702840 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2154. Min Act: -0.1700
Data Index: 3543857 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.2154. Min Act: -0.1700
Data Index: 5374119 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.1842. Min Act: -0.1700
Data Index: 3643977 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.1842. Min Act: -0.1700
Data Index: 2188217 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.1842. Min Act: -0.1700
Data Index: 7575439 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.1842. Min Act: -0.1700
Data Index: 2736337 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.1529. Min Act: -0.1700
Data Index: 5667347 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4967. Min Range: -4.4967
Max Act: 4.1217. Min Act: -0.1700
Data Index: 1118506 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19