Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1922. Min Range: -10.1922
Max Act: 10.1922. Min Act: -0.1700
Data Index: 2124555 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.8797. Min Act: -0.1700
Data Index: 715249 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.9422. Min Act: -0.1700
Data Index: 5869324 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.7547. Min Act: -0.1700
Data Index: 4080367 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.6922. Min Act: -0.1700
Data Index: 7983422 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.6297. Min Act: -0.1700
Data Index: 5275934 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.6297. Min Act: -0.1700
Data Index: 5348845 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.6297. Min Act: -0.1700
Data Index: 617359 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5672. Min Act: -0.1700
Data Index: 8803893 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5672. Min Act: -0.1700
Data Index: 6151412 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5672. Min Act: -0.1700
Data Index: 143207 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5047. Min Act: -0.1700
Data Index: 7735760 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5047. Min Act: -0.1700
Data Index: 7842336 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5047. Min Act: -0.1700
Data Index: 430641 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5047. Min Act: -0.1700
Data Index: 2711408 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.5047. Min Act: -0.1700
Data Index: 2617053 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.4422. Min Act: -0.1700
Data Index: 1070891 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.4422. Min Act: -0.1700
Data Index: 3275502 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.4422. Min Act: -0.1700
Data Index: 7298811 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1922. Min Range: -10.1922
Max Act: 9.4422. Min Act: -0.1700
Data Index: 6129263 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19