Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 627 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0087. Min Range: -7.0087
Max Act: 7.0087. Min Act: -0.1700
Data Index: 8570770 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.9150. Min Act: -0.1700
Data Index: 635221 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.9150. Min Act: -0.1700
Data Index: 2462878 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.8837. Min Act: -0.1700
Data Index: 3504881 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.8837. Min Act: -0.1700
Data Index: 7894921 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.8525. Min Act: -0.1700
Data Index: 1620683 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.8525. Min Act: -0.1700
Data Index: 1361549 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7900. Min Act: -0.1700
Data Index: 3003096 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7900. Min Act: -0.1700
Data Index: 4660015 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7900. Min Act: -0.1700
Data Index: 6297123 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7900. Min Act: -0.1700
Data Index: 4208016 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7900. Min Act: -0.1700
Data Index: 4577457 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7587. Min Act: -0.1700
Data Index: 7610352 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7275. Min Act: -0.1700
Data Index: 476683 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7587. Min Act: -0.1700
Data Index: 2836104 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7587. Min Act: -0.1700
Data Index: 818494 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7275. Min Act: -0.1700
Data Index: 5199689 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7275. Min Act: -0.1700
Data Index: 7309431 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7275. Min Act: -0.1700
Data Index: 3210298 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0087. Min Range: -7.0087
Max Act: 6.7275. Min Act: -0.1700
Data Index: 3603856 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19