Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6276 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.4110. Min Act: -0.1700
Data Index: 142734 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4110. Min Range: -6.4110
Max Act: 6.2235. Min Act: -0.1700
Data Index: 1722180 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.9735. Min Act: -0.1700
Data Index: 2638489 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.9735. Min Act: -0.1700
Data Index: 5542441 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.9735. Min Act: -0.1700
Data Index: 295928 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.9423. Min Act: -0.1700
Data Index: 1751493 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8798. Min Act: -0.1700
Data Index: 6569235 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.9110. Min Act: -0.1700
Data Index: 2298824 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.9110. Min Act: -0.1700
Data Index: 8429956 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.9423. Min Act: -0.1700
Data Index: 5387161 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8798. Min Act: -0.1700
Data Index: 7213555 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8485. Min Act: -0.1700
Data Index: 372180 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8485. Min Act: -0.1700
Data Index: 8238772 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8173. Min Act: -0.1700
Data Index: 8233817 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8173. Min Act: -0.1700
Data Index: 7773297 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1774915 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1195957 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.7860. Min Act: -0.1700
Data Index: 179629 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.7548. Min Act: -0.1700
Data Index: 372174 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4110. Min Range: -6.4110
Max Act: 5.7860. Min Act: -0.1700
Data Index: 8253878 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19