Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 887 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3402. Min Range: -7.3402
Max Act: 7.3402. Min Act: -0.1700
Data Index: 7550693 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.9027. Min Act: -0.1700
Data Index: 6850440 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.8715. Min Act: -0.1700
Data Index: 3829885 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.8715. Min Act: -0.1700
Data Index: 5732944 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.8402. Min Act: -0.1700
Data Index: 3408793 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.8402. Min Act: -0.1700
Data Index: 4337351 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.8090. Min Act: -0.1700
Data Index: 8276889 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.8090. Min Act: -0.1700
Data Index: 2640251 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.8090. Min Act: -0.1700
Data Index: 757888 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.7777. Min Act: -0.1700
Data Index: 188861 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.7465. Min Act: -0.1700
Data Index: 346507 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.7152. Min Act: -0.1700
Data Index: 3930935 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.7152. Min Act: -0.1700
Data Index: 1081929 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.7152. Min Act: -0.1700
Data Index: 8212770 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.7465. Min Act: -0.1700
Data Index: 3842448 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.7152. Min Act: -0.1700
Data Index: 828344 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.6527. Min Act: -0.1700
Data Index: 2446737 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.6527. Min Act: -0.1700
Data Index: 4895762 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.6527. Min Act: -0.1700
Data Index: 3183001 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3402. Min Range: -7.3402
Max Act: 6.6527. Min Act: -0.1700
Data Index: 5532667 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19