Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.5515. Min Act: -0.1700
Data Index: 1082309 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.4890. Min Act: -0.1700
Data Index: 5963244 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.3952. Min Act: -0.1700
Data Index: 1610086 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.3640. Min Act: -0.1700
Data Index: 8510302 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.3640. Min Act: -0.1700
Data Index: 5538606 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.3327. Min Act: -0.1700
Data Index: 5679698 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.3640. Min Act: -0.1700
Data Index: 8229760 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.3015. Min Act: -0.1700
Data Index: 2298967 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.3327. Min Act: -0.1700
Data Index: 1362733 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2390. Min Act: -0.1700
Data Index: 849351 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2702. Min Act: -0.1700
Data Index: 6282950 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2702. Min Act: -0.1700
Data Index: 799611 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2702. Min Act: -0.1700
Data Index: 8771461 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2390. Min Act: -0.1700
Data Index: 2525282 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2390. Min Act: -0.1700
Data Index: 3840147 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2390. Min Act: -0.1700
Data Index: 2314878 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.1765. Min Act: -0.1700
Data Index: 8745396 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2077. Min Act: -0.1700
Data Index: 1662945 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.2077. Min Act: -0.1700
Data Index: 7255233 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5515. Min Range: -5.5515
Max Act: 5.1765. Min Act: -0.1700
Data Index: 4112592 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19