Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.9556. Min Act: -0.1700
Data Index: 8613838 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.7681. Min Act: -0.1697
Data Index: 3682739 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.7056. Min Act: -0.1700
Data Index: 3238535 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.7056. Min Act: -0.1700
Data Index: 7456301 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.6431. Min Act: -0.1700
Data Index: 97960 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.6431. Min Act: -0.1700
Data Index: 7266297 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.6431. Min Act: -0.1700
Data Index: 1037766 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.7056. Min Act: -0.1700
Data Index: 2587768 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.6431. Min Act: -0.1699
Data Index: 7886383 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.5806. Min Act: -0.1700
Data Index: 1147094 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.4556. Min Act: -0.1700
Data Index: 617330 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.5181. Min Act: -0.1700
Data Index: 1394575 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.5181. Min Act: -0.1700
Data Index: 1286706 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.5181. Min Act: -0.1700
Data Index: 286449 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.5181. Min Act: -0.1700
Data Index: 2503250 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.5181. Min Act: -0.1700
Data Index: 6782698 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.4556. Min Act: -0.1699
Data Index: 2755371 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.4556. Min Act: -0.1699
Data Index: 1216084 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.4556. Min Act: -0.1700
Data Index: 1042150 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9556. Min Range: -8.9556
Max Act: 8.4556. Min Act: -0.1700
Data Index: 1138114 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19