Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.4425. Min Act: -0.1700
Data Index: 6819102 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.4425. Min Act: -0.1700
Data Index: 3982925 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.4425. Min Act: -0.1700
Data Index: 3342365 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.3175. Min Act: -0.1700
Data Index: 4299467 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1300. Min Act: -0.1700
Data Index: 6239639 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1300. Min Act: -0.1700
Data Index: 5634625 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1300. Min Act: -0.1700
Data Index: 5630025 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0988. Min Act: -0.1700
Data Index: 6220256 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0988. Min Act: -0.1700
Data Index: 5392178 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0675. Min Act: -0.1700
Data Index: 3238141 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0675. Min Act: -0.1700
Data Index: 8500085 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0363. Min Act: -0.1700
Data Index: 3803192 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0363. Min Act: -0.1700
Data Index: 6365851 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0363. Min Act: -0.1700
Data Index: 4890506 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4425. Min Range: -5.4425
Max Act: 4.9738. Min Act: -0.1700
Data Index: 231009 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0050. Min Act: -0.1700
Data Index: 4377221 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4425. Min Range: -5.4425
Max Act: 4.9738. Min Act: -0.1700
Data Index: 8298292 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.0050. Min Act: -0.1700
Data Index: 183025 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4425. Min Range: -5.4425
Max Act: 4.9738. Min Act: -0.1700
Data Index: 6388878 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4425. Min Range: -5.4425
Max Act: 4.9738. Min Act: -0.1700
Data Index: 2556466 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19