Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1685 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.7418. Min Act: -0.1700
Data Index: 2988776 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.4293. Min Act: -0.1700
Data Index: 2657840 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.3355. Min Act: -0.1700
Data Index: 683469 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.3043. Min Act: -0.1700
Data Index: 5454861 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.2105. Min Act: -0.1700
Data Index: 941310 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.2105. Min Act: -0.1700
Data Index: 2484402 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.1793. Min Act: -0.1700
Data Index: 7592086 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.1168. Min Act: -0.1700
Data Index: 5887972 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.1480. Min Act: -0.1700
Data Index: 2107732 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.1168. Min Act: -0.1700
Data Index: 4132156 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.1480. Min Act: -0.1700
Data Index: 1864590 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.0855. Min Act: -0.1700
Data Index: 8624364 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.0855. Min Act: -0.1700
Data Index: 6908658 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.0855. Min Act: -0.1700
Data Index: 13055 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.0543. Min Act: -0.1700
Data Index: 6949944 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.0543. Min Act: -0.1700
Data Index: 8515393 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.0543. Min Act: -0.1700
Data Index: 6085943 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7418. Min Range: -6.7418
Max Act: 6.0230. Min Act: -0.1700
Data Index: 6908659 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7418. Min Range: -6.7418
Max Act: 5.9605. Min Act: -0.1700
Data Index: 2546915 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7418. Min Range: -6.7418
Max Act: 5.9918. Min Act: -0.1700
Data Index: 1646960 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19