Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4446 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4255. Min Range: -8.4255
Max Act: 8.4255. Min Act: -0.1700
Data Index: 2743782 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4255. Min Range: -8.4255
Max Act: 8.3630. Min Act: -0.1700
Data Index: 4527896 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4255. Min Range: -8.4255
Max Act: 8.3630. Min Act: -0.1700
Data Index: 4333455 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4255. Min Range: -8.4255
Max Act: 8.1130. Min Act: -0.1700
Data Index: 2333862 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.9880. Min Act: -0.1700
Data Index: 3121455 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.9880. Min Act: -0.1700
Data Index: 6621744 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.9880. Min Act: -0.1700
Data Index: 8439161 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.9255. Min Act: -0.1700
Data Index: 2000758 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.8005. Min Act: -0.1700
Data Index: 6242673 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.8005. Min Act: -0.1700
Data Index: 4251190 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.8005. Min Act: -0.1700
Data Index: 3885414 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.8005. Min Act: -0.1700
Data Index: 5826961 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.8005. Min Act: -0.1700
Data Index: 7983482 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.8005. Min Act: -0.1700
Data Index: 3466201 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.8005. Min Act: -0.1700
Data Index: 7189982 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.7380. Min Act: -0.1700
Data Index: 315399 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.7380. Min Act: -0.1700
Data Index: 4718254 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.7380. Min Act: -0.1700
Data Index: 3842736 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.7380. Min Act: -0.1700
Data Index: 7400951 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4255. Min Range: -8.4255
Max Act: 7.7380. Min Act: -0.1700
Data Index: 2044130 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19