Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1777. Min Range: -6.1777
Max Act: 6.1777. Min Act: -0.1700
Data Index: 2534187 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.7402. Min Act: -0.1700
Data Index: 5346219 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.5214. Min Act: -0.1700
Data Index: 7768814 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.4902. Min Act: -0.1700
Data Index: 5673416 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.4589. Min Act: -0.1700
Data Index: 5850315 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.4589. Min Act: -0.1700
Data Index: 2484699 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.4277. Min Act: -0.1700
Data Index: 6428299 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3652. Min Act: -0.1700
Data Index: 6084108 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3070845 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3133267 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3027. Min Act: -0.1700
Data Index: 5658780 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3339. Min Act: -0.1700
Data Index: 8662556 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3339. Min Act: -0.1700
Data Index: 1032184 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3339. Min Act: -0.1700
Data Index: 6517540 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3027. Min Act: -0.1700
Data Index: 7831713 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.3339. Min Act: -0.1700
Data Index: 6592884 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.2714. Min Act: -0.1700
Data Index: 718779 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.2714. Min Act: -0.1700
Data Index: 7961899 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.2714. Min Act: -0.1700
Data Index: 6065813 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1777. Min Range: -6.1777
Max Act: 5.2402. Min Act: -0.1700
Data Index: 2008527 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19