Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5815 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.7531. Min Act: -0.1700
Data Index: 60770 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.7531. Min Act: -0.1700
Data Index: 5392495 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.6906. Min Act: -0.1700
Data Index: 6519322 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.6594. Min Act: -0.1700
Data Index: 2109421 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.6594. Min Act: -0.1700
Data Index: 4906589 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5969. Min Act: -0.1700
Data Index: 4351343 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5656. Min Act: -0.1700
Data Index: 2620572 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5656. Min Act: -0.1700
Data Index: 2853631 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5344. Min Act: -0.1700
Data Index: 4171977 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5656. Min Act: -0.1700
Data Index: 3307725 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.5344. Min Act: -0.1700
Data Index: 8701595 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4719. Min Act: -0.1700
Data Index: 7951576 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4719. Min Act: -0.1700
Data Index: 746604 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4406. Min Act: -0.1700
Data Index: 5107147 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4406. Min Act: -0.1700
Data Index: 520137 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4406. Min Act: -0.1700
Data Index: 7720048 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4719. Min Act: -0.1700
Data Index: 8302576 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4406. Min Act: -0.1700
Data Index: 6358794 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4094. Min Act: -0.1700
Data Index: 6324262 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7531. Min Range: -4.7531
Max Act: 4.4094. Min Act: -0.1700
Data Index: 8479524 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19