Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 877 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.7090. Min Act: -0.1700
Data Index: 1379526 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.4902. Min Act: -0.1700
Data Index: 2061291 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.3965. Min Act: -0.1700
Data Index: 734194 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.3965. Min Act: -0.1700
Data Index: 5341205 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.3652. Min Act: -0.1700
Data Index: 6710598 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.3027. Min Act: -0.1700
Data Index: 7873884 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.1152. Min Act: -0.1700
Data Index: 1626153 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.0527. Min Act: -0.1700
Data Index: 7754591 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.0527. Min Act: -0.1700
Data Index: 8479211 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.0527. Min Act: -0.1700
Data Index: 6514424 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.0527. Min Act: -0.1700
Data Index: 4862280 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.0215. Min Act: -0.1700
Data Index: 6548402 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7090. Min Range: -7.7090
Max Act: 6.9902. Min Act: -0.1700
Data Index: 1317277 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7090. Min Range: -7.7090
Max Act: 7.0215. Min Act: -0.1700
Data Index: 5159477 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7090. Min Range: -7.7090
Max Act: 6.9590. Min Act: -0.1700
Data Index: 3353473 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7090. Min Range: -7.7090
Max Act: 6.9590. Min Act: -0.1700
Data Index: 7643118 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7090. Min Range: -7.7090
Max Act: 6.9590. Min Act: -0.1700
Data Index: 4340268 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7090. Min Range: -7.7090
Max Act: 6.9277. Min Act: -0.1700
Data Index: 598142 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7090. Min Range: -7.7090
Max Act: 6.9277. Min Act: -0.1700
Data Index: 7595049 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7090. Min Range: -7.7090
Max Act: 6.8965. Min Act: -0.1700
Data Index: 1168114 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19