Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4872 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.8093. Min Act: -0.1700
Data Index: 479150 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.7468. Min Act: -0.1700
Data Index: 7470642 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.6843. Min Act: -0.1700
Data Index: 3986335 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.6843. Min Act: -0.1700
Data Index: 8227500 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.5280. Min Act: -0.1700
Data Index: 4618238 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.4968. Min Act: -0.1700
Data Index: 5487707 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.4343. Min Act: -0.1700
Data Index: 5370025 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.4030. Min Act: -0.1700
Data Index: 8311070 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.4030. Min Act: -0.1700
Data Index: 8294217 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.3718. Min Act: -0.1700
Data Index: 4176643 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.3405. Min Act: -0.1700
Data Index: 7169363 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.3093. Min Act: -0.1700
Data Index: 7826789 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.3405. Min Act: -0.1700
Data Index: 8733886 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.3093. Min Act: -0.1700
Data Index: 3126003 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.2780. Min Act: -0.1700
Data Index: 4210297 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.2780. Min Act: -0.1700
Data Index: 7706349 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.2780. Min Act: -0.1700
Data Index: 627465 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.2780. Min Act: -0.1700
Data Index: 6832116 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.2780. Min Act: -0.1700
Data Index: 4891245 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8093. Min Range: -5.8093
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7307845 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19