Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3151 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4096. Min Range: -6.4096
Max Act: 6.4096. Min Act: -0.1700
Data Index: 8516697 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4096. Min Range: -6.4096
Max Act: 6.0971. Min Act: -0.1700
Data Index: 8786988 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.9721. Min Act: -0.1700
Data Index: 3191354 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.8158. Min Act: -0.1700
Data Index: 6193117 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.7221. Min Act: -0.1700
Data Index: 2985282 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.7533. Min Act: -0.1700
Data Index: 866090 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.6908. Min Act: -0.1700
Data Index: 7270258 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.6908. Min Act: -0.1700
Data Index: 6430031 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.6908. Min Act: -0.1700
Data Index: 311120 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.6596. Min Act: -0.1700
Data Index: 2039443 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5971. Min Act: -0.1700
Data Index: 3666962 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5971. Min Act: -0.1700
Data Index: 4188430 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5971. Min Act: -0.1700
Data Index: 3907644 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5346. Min Act: -0.1700
Data Index: 7664783 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 5553044 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 7785649 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5346. Min Act: -0.1700
Data Index: 5361054 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 916800 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.5033. Min Act: -0.1700
Data Index: 2700669 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4096. Min Range: -6.4096
Max Act: 5.4721. Min Act: -0.1700
Data Index: 445226 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19