Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.7781. Min Act: -0.1700
Data Index: 1891746 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.6373. Min Act: -0.1700
Data Index: 4826886 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.5277. Min Act: -0.1700
Data Index: 2065912 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.5434. Min Act: -0.1700
Data Index: 583549 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.5277. Min Act: -0.1700
Data Index: 7967747 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.4964. Min Act: -0.1700
Data Index: 5199181 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.4181. Min Act: -0.1700
Data Index: 4077400 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.4181. Min Act: -0.1700
Data Index: 322671 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.4181. Min Act: -0.1700
Data Index: 8758362 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.4024. Min Act: -0.1700
Data Index: 1244524 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.4024. Min Act: -0.1700
Data Index: 2329064 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.4024. Min Act: -0.1700
Data Index: 6242448 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3553. Min Act: -0.1700
Data Index: 5966290 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3553. Min Act: -0.1700
Data Index: 8101239 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3396. Min Act: -0.1700
Data Index: 4415436 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3396. Min Act: -0.1700
Data Index: 8411209 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3553. Min Act: -0.1700
Data Index: 4532771 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3396. Min Act: -0.1700
Data Index: 5760687 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3553. Min Act: -0.1700
Data Index: 7171877 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7781. Min Range: -3.7781
Max Act: 3.3396. Min Act: -0.1700
Data Index: 7506791 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19