Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5376 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.7496. Min Act: -0.1700
Data Index: 72400 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.7808. Min Act: -0.1700
Data Index: 8764086 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.6871. Min Act: -0.1700
Data Index: 327115 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.6558. Min Act: -0.1700
Data Index: 195353 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.6558. Min Act: -0.1700
Data Index: 4864976 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.6246. Min Act: -0.1700
Data Index: 1834979 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.5933. Min Act: -0.1700
Data Index: 7538799 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.5621. Min Act: -0.1697
Data Index: 8368873 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.5621. Min Act: -0.1700
Data Index: 7185514 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4996. Min Act: -0.1700
Data Index: 4990014 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.5308. Min Act: -0.1700
Data Index: 6540583 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.5308. Min Act: -0.1700
Data Index: 2258883 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.5308. Min Act: -0.1700
Data Index: 3501242 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4996. Min Act: -0.1700
Data Index: 8617766 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4996. Min Act: -0.1700
Data Index: 2194615 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 910043 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 1890040 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 4589917 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 3352890 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7808. Min Range: -5.7808
Max Act: 5.4683. Min Act: -0.1700
Data Index: 206319 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19