Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4902 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1555. Min Range: -6.1555
Max Act: 6.1555. Min Act: -0.1700
Data Index: 8245780 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1555. Min Range: -6.1555
Max Act: 6.0617. Min Act: -0.1700
Data Index: 6067717 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1555. Min Range: -6.1555
Max Act: 6.0305. Min Act: -0.1700
Data Index: 3823334 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9367. Min Act: -0.1700
Data Index: 4931295 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9055. Min Act: -0.1700
Data Index: 5201450 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9367. Min Act: -0.1700
Data Index: 1400005 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.9680. Min Act: -0.1700
Data Index: 4531635 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.8742. Min Act: -0.1700
Data Index: 8698154 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7805. Min Act: -0.1700
Data Index: 5313044 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7492. Min Act: -0.1700
Data Index: 1185584 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4472274 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7180. Min Act: -0.1700
Data Index: 6618494 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7180. Min Act: -0.1700
Data Index: 1222873 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7180. Min Act: -0.1700
Data Index: 7182731 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.7180. Min Act: -0.1700
Data Index: 5418357 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.6867. Min Act: -0.1700
Data Index: 6071402 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.6555. Min Act: -0.1700
Data Index: 1609703 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.6867. Min Act: -0.1700
Data Index: 4013503 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.6867. Min Act: -0.1700
Data Index: 915119 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1555. Min Range: -6.1555
Max Act: 5.6555. Min Act: -0.1700
Data Index: 7417885 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19