Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1041 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0230. Min Range: -4.0230
Max Act: 4.0230. Min Act: -0.1700
Data Index: 3617828 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.9605. Min Act: -0.1700
Data Index: 5128377 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.9605. Min Act: -0.1700
Data Index: 8577468 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8980. Min Act: -0.1700
Data Index: 3022745 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8823. Min Act: -0.1700
Data Index: 6397463 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8980. Min Act: -0.1700
Data Index: 7408139 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8980. Min Act: -0.1700
Data Index: 4360152 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8823. Min Act: -0.1700
Data Index: 4551262 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8667. Min Act: -0.1700
Data Index: 1638457 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8510. Min Act: -0.1700
Data Index: 1925176 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8198. Min Act: -0.1700
Data Index: 8494115 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8198. Min Act: -0.1700
Data Index: 8806673 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8041. Min Act: -0.1700
Data Index: 694825 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.8041. Min Act: -0.1700
Data Index: 81944 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.7885. Min Act: -0.1700
Data Index: 4121971 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.7729. Min Act: -0.1700
Data Index: 1895532 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.7729. Min Act: -0.1700
Data Index: 5625826 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.7729. Min Act: -0.1700
Data Index: 2033278 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.7572. Min Act: -0.1700
Data Index: 2839488 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0230. Min Range: -4.0230
Max Act: 3.7416. Min Act: -0.1700
Data Index: 3219996 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19