Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.6276. Min Act: -0.1700
Data Index: 1040608 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.6276. Min Act: -0.1700
Data Index: 6602549 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.5339. Min Act: -0.1700
Data Index: 1167836 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.4714. Min Act: -0.1700
Data Index: 4216599 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.3776. Min Act: -0.1700
Data Index: 6423220 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.3151. Min Act: -0.1700
Data Index: 1040607 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.2839. Min Act: -0.1700
Data Index: 6602551 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.2839. Min Act: -0.1700
Data Index: 679198 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.2839. Min Act: -0.1700
Data Index: 5172079 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.2526. Min Act: -0.1700
Data Index: 1867813 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.2526. Min Act: -0.1700
Data Index: 6602550 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1901. Min Act: -0.1700
Data Index: 8574207 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.2214. Min Act: -0.1700
Data Index: 1679875 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1901. Min Act: -0.1700
Data Index: 6567635 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1901. Min Act: -0.1700
Data Index: 3742633 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1901. Min Act: -0.1700
Data Index: 8424811 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1589. Min Act: -0.1700
Data Index: 6594748 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1589. Min Act: -0.1700
Data Index: 4080001 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1589. Min Act: -0.1700
Data Index: 8575964 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6276. Min Range: -5.6276
Max Act: 5.1589. Min Act: -0.1700
Data Index: 5739418 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19