Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4697 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.5279. Min Act: -0.1700
Data Index: 7729699 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.4029. Min Act: -0.1700
Data Index: 4168029 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.3091. Min Act: -0.1700
Data Index: 44787 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.2466. Min Act: -0.1700
Data Index: 5483407 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.1841. Min Act: -0.1700
Data Index: 2406612 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.1216. Min Act: -0.1700
Data Index: 8191271 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.0904. Min Act: -0.1700
Data Index: 6862316 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.0904. Min Act: -0.1700
Data Index: 1477679 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.0591. Min Act: -0.1700
Data Index: 44788 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.0279. Min Act: -0.1700
Data Index: 3876918 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.0904. Min Act: -0.1700
Data Index: 6268571 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5279. Min Range: -5.5279
Max Act: 5.0279. Min Act: -0.1700
Data Index: 3253529 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9654. Min Act: -0.1700
Data Index: 4888515 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9654. Min Act: -0.1700
Data Index: 3446860 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9341. Min Act: -0.1700
Data Index: 556601 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9654. Min Act: -0.1700
Data Index: 3656752 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9341. Min Act: -0.1700
Data Index: 4320558 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9341. Min Act: -0.1700
Data Index: 8617656 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9341. Min Act: -0.1700
Data Index: 8646505 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5279. Min Range: -5.5279
Max Act: 4.9341. Min Act: -0.1700
Data Index: 1104844 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19