Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1108. Min Range: -10.1108
Max Act: 10.1108. Min Act: -0.1700
Data Index: 1785779 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.9233. Min Act: -0.1700
Data Index: 1972236 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.9233. Min Act: -0.1700
Data Index: 1785780 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.6733. Min Act: -0.1700
Data Index: 2492410 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.6108. Min Act: -0.1700
Data Index: 5565137 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.4233. Min Act: -0.1700
Data Index: 7801400 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.4233. Min Act: -0.1700
Data Index: 6634867 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.2983. Min Act: -0.1700
Data Index: 4081707 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.2983. Min Act: -0.1700
Data Index: 661386 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.2358. Min Act: -0.1700
Data Index: 4068698 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.2358. Min Act: -0.1700
Data Index: 2492411 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.2358. Min Act: -0.1700
Data Index: 4068710 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.2358. Min Act: -0.1700
Data Index: 7331011 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.1108. Min Act: -0.1700
Data Index: 399727 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.1733. Min Act: -0.1700
Data Index: 6311817 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.1733. Min Act: -0.1700
Data Index: 1185299 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.1733. Min Act: -0.1700
Data Index: 7111273 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.1733. Min Act: -0.1700
Data Index: 1352988 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.1733. Min Act: -0.1700
Data Index: 3216730 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1108. Min Range: -10.1108
Max Act: 9.1108. Min Act: -0.1700
Data Index: 5040488 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19