Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.8069. Min Act: -0.1700
Data Index: 7742747 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.7443. Min Act: -0.1700
Data Index: 220758 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.6818. Min Act: -0.1700
Data Index: 6268728 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.6505. Min Act: -0.1700
Data Index: 8722158 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.6192. Min Act: -0.1700
Data Index: 6988255 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5566. Min Act: -0.1700
Data Index: 416003 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5879. Min Act: -0.1700
Data Index: 1618076 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5566. Min Act: -0.1700
Data Index: 6097087 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5566. Min Act: -0.1700
Data Index: 3765997 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5566. Min Act: -0.1700
Data Index: 7885865 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5566. Min Act: -0.1700
Data Index: 287201 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5879. Min Act: -0.1700
Data Index: 6881311 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5566. Min Act: -0.1700
Data Index: 2438789 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5253. Min Act: -0.1700
Data Index: 1100773 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.4939. Min Act: -0.1700
Data Index: 1094265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5253. Min Act: -0.1700
Data Index: 1815788 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5253. Min Act: -0.1700
Data Index: 8700863 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5253. Min Act: -0.1700
Data Index: 4014517 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5253. Min Act: -0.1700
Data Index: 7025490 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8069. Min Range: -3.8069
Max Act: 3.5253. Min Act: -0.1700
Data Index: 6768884 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19