Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2111. Min Range: -5.2111
Max Act: 5.2111. Min Act: -0.1700
Data Index: 3435025 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2111. Min Range: -5.2111
Max Act: 5.1174. Min Act: -0.1700
Data Index: 295893 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2111. Min Range: -5.2111
Max Act: 5.0549. Min Act: -0.1700
Data Index: 7920877 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2111. Min Range: -5.2111
Max Act: 5.0549. Min Act: -0.1700
Data Index: 4808884 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.9924. Min Act: -0.1700
Data Index: 1935274 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.9924. Min Act: -0.1700
Data Index: 3369645 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.9611. Min Act: -0.1700
Data Index: 6533579 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.9299. Min Act: -0.1700
Data Index: 847132 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.9299. Min Act: -0.1700
Data Index: 7920874 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.8986. Min Act: -0.1700
Data Index: 8536470 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.8986. Min Act: -0.1700
Data Index: 2478983 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.8674. Min Act: -0.1700
Data Index: 1768132 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.8361. Min Act: -0.1700
Data Index: 8536472 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.8361. Min Act: -0.1700
Data Index: 7777148 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.8049. Min Act: -0.1700
Data Index: 8656812 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.7736. Min Act: -0.1700
Data Index: 3667695 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.7736. Min Act: -0.1700
Data Index: 702036 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.7736. Min Act: -0.1700
Data Index: 7506846 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.7424. Min Act: -0.1700
Data Index: 6740561 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2111. Min Range: -5.2111
Max Act: 4.7111. Min Act: -0.1700
Data Index: 112867 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19