Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 832 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.8859. Min Act: -0.1700
Data Index: 4498979 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.8859. Min Act: -0.1700
Data Index: 6290363 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.7609. Min Act: -0.1700
Data Index: 4648240 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.8234. Min Act: -0.1700
Data Index: 8021436 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.6984. Min Act: -0.1700
Data Index: 1543996 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.6984. Min Act: -0.1700
Data Index: 5598737 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.6359. Min Act: -0.1700
Data Index: 4990483 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.5734. Min Act: -0.1700
Data Index: 2156565 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.5109. Min Act: -0.1700
Data Index: 5368804 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.5109. Min Act: -0.1700
Data Index: 6572400 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.5109. Min Act: -0.1700
Data Index: 4179752 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.4484. Min Act: -0.1700
Data Index: 1225899 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.3859. Min Act: -0.1700
Data Index: 4854694 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.3859. Min Act: -0.1700
Data Index: 291158 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.3859. Min Act: -0.1700
Data Index: 1952218 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.3859. Min Act: -0.1700
Data Index: 7671685 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.3859. Min Act: -0.1700
Data Index: 6839562 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.3859. Min Act: -0.1700
Data Index: 4688086 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.4484. Min Act: -0.1700
Data Index: 3559090 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8859. Min Range: -9.8859
Max Act: 9.3859. Min Act: -0.1700
Data Index: 2277273 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19