Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5022 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.2051. Min Act: -0.1700
Data Index: 8611921 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.2051. Min Act: -0.1700
Data Index: 4561604 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.2051. Min Act: -0.1700
Data Index: 6678706 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.2051. Min Act: -0.1700
Data Index: 7115942 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.1426. Min Act: -0.1700
Data Index: 5435319 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.1426. Min Act: -0.1700
Data Index: 2123280 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.1426. Min Act: -0.1700
Data Index: 3380914 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.1426. Min Act: -0.1700
Data Index: 5466853 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0801. Min Act: -0.1700
Data Index: 6423119 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.1114. Min Act: -0.1700
Data Index: 6305386 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.1114. Min Act: -0.1700
Data Index: 2277297 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0489. Min Act: -0.1700
Data Index: 7390456 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0801. Min Act: -0.1700
Data Index: 5153796 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0489. Min Act: -0.1700
Data Index: 4809398 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0801. Min Act: -0.1700
Data Index: 3154876 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0489. Min Act: -0.1700
Data Index: 4127379 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0489. Min Act: -0.1700
Data Index: 3998323 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0489. Min Act: -0.1700
Data Index: 2712139 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0489. Min Act: -0.1700
Data Index: 418082 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2051. Min Range: -5.2051
Max Act: 5.0801. Min Act: -0.1700
Data Index: 4146746 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19