Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5372 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.9743. Min Act: -0.1700
Data Index: 4855140 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.8806. Min Act: -0.1700
Data Index: 2636768 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.8181. Min Act: -0.1700
Data Index: 8063918 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.7556. Min Act: -0.1700
Data Index: 6267149 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.7556. Min Act: -0.1700
Data Index: 7624303 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.7243. Min Act: -0.1700
Data Index: 5088273 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5993. Min Act: -0.1700
Data Index: 124261 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5681. Min Act: -0.1700
Data Index: 1763598 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5681. Min Act: -0.1700
Data Index: 7833225 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5368. Min Act: -0.1700
Data Index: 4472933 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5368. Min Act: -0.1700
Data Index: 471376 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5056. Min Act: -0.1700
Data Index: 1863835 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.4743. Min Act: -0.1700
Data Index: 7495769 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5056. Min Act: -0.1700
Data Index: 8334378 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5056. Min Act: -0.1700
Data Index: 40038 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.5056. Min Act: -0.1700
Data Index: 7214326 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.4743. Min Act: -0.1700
Data Index: 2902535 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.4743. Min Act: -0.1700
Data Index: 5004782 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.4743. Min Act: -0.1700
Data Index: 7392400 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9743. Min Range: -6.9743
Max Act: 6.4743. Min Act: -0.1700
Data Index: 7657569 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19