Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.9982. Min Act: -0.1700
Data Index: 2541021 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.8732. Min Act: -0.1700
Data Index: 7958295 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.9044. Min Act: -0.1700
Data Index: 2951182 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6857. Min Act: -0.1700
Data Index: 4877731 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6544. Min Act: -0.1700
Data Index: 788856 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.6232. Min Act: -0.1700
Data Index: 7261666 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.5919. Min Act: -0.1700
Data Index: 3721442 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.5607. Min Act: -0.1700
Data Index: 297269 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.5294. Min Act: -0.1700
Data Index: 5644779 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4982. Min Act: -0.1700
Data Index: 1659345 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4982. Min Act: -0.1700
Data Index: 722303 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4669. Min Act: -0.1700
Data Index: 6001683 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4669. Min Act: -0.1700
Data Index: 215662 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4669. Min Act: -0.1700
Data Index: 6282709 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4669. Min Act: -0.1700
Data Index: 6951842 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4669. Min Act: -0.1700
Data Index: 2256184 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4044. Min Act: -0.1700
Data Index: 740695 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4357. Min Act: -0.1700
Data Index: 5614308 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4044. Min Act: -0.1700
Data Index: 4463837 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9982. Min Range: -4.9982
Max Act: 4.4357. Min Act: -0.1700
Data Index: 81089 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19