Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1099 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0865. Min Range: -8.0865
Max Act: 8.0865. Min Act: -0.1700
Data Index: 854796 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.8365. Min Act: -0.1700
Data Index: 4350429 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.7427. Min Act: -0.1700
Data Index: 7303794 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.7427. Min Act: -0.1700
Data Index: 5264966 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.6490. Min Act: -0.1700
Data Index: 5434990 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.6490. Min Act: -0.1700
Data Index: 506242 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.5865. Min Act: -0.1700
Data Index: 2553928 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.5552. Min Act: -0.1700
Data Index: 845180 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.5552. Min Act: -0.1700
Data Index: 5875983 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.4615. Min Act: -0.1700
Data Index: 2686668 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.4927. Min Act: -0.1700
Data Index: 8219795 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.4615. Min Act: -0.1700
Data Index: 7341570 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.4302. Min Act: -0.1700
Data Index: 3161662 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.3990. Min Act: -0.1700
Data Index: 4004888 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.3365. Min Act: -0.1700
Data Index: 2537545 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.3365. Min Act: -0.1700
Data Index: 1827864 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.3365. Min Act: -0.1700
Data Index: 2807704 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.3052. Min Act: -0.1700
Data Index: 720033 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.3052. Min Act: -0.1700
Data Index: 6656854 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0865. Min Range: -8.0865
Max Act: 7.3052. Min Act: -0.1700
Data Index: 3790118 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19