Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2204 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.9401. Min Act: -0.1700
Data Index: 5566861 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.7838. Min Act: -0.1700
Data Index: 202723 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.7526. Min Act: -0.1700
Data Index: 2625306 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.5651. Min Act: -0.1700
Data Index: 2003850 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.5338. Min Act: -0.1700
Data Index: 5778439 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.4713. Min Act: -0.1700
Data Index: 5767557 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.4713. Min Act: -0.1700
Data Index: 7395748 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.4401. Min Act: -0.1700
Data Index: 3502173 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.4401. Min Act: -0.1700
Data Index: 3305723 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.4088. Min Act: -0.1700
Data Index: 8488016 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.4088. Min Act: -0.1700
Data Index: 8319387 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.3776. Min Act: -0.1700
Data Index: 1098885 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.3463. Min Act: -0.1700
Data Index: 7603327 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.3151. Min Act: -0.1700
Data Index: 3641163 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.3151. Min Act: -0.1700
Data Index: 5299461 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.3151. Min Act: -0.1700
Data Index: 1116226 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.2838. Min Act: -0.1700
Data Index: 7907120 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.2838. Min Act: -0.1700
Data Index: 1631723 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.2213. Min Act: -0.1700
Data Index: 6433437 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9401. Min Range: -6.9401
Max Act: 6.2838. Min Act: -0.1700
Data Index: 76690 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19