Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2054 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.5977. Min Act: -0.1700
Data Index: 6057966 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.5664. Min Act: -0.1700
Data Index: 6459233 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.5039. Min Act: -0.1700
Data Index: 5789913 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.4727. Min Act: -0.1700
Data Index: 2054486 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.4727. Min Act: -0.1700
Data Index: 696986 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.3789. Min Act: -0.1700
Data Index: 8262397 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.3477. Min Act: -0.1700
Data Index: 2415981 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.3164. Min Act: -0.1700
Data Index: 5223175 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.3164. Min Act: -0.1700
Data Index: 4773670 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.3477. Min Act: -0.1700
Data Index: 75674 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.2852. Min Act: -0.1700
Data Index: 7471189 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6000949 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.2852. Min Act: -0.1700
Data Index: 4417269 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.2852. Min Act: -0.1700
Data Index: 4349389 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.2227. Min Act: -0.1700
Data Index: 4557879 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.1914. Min Act: -0.1700
Data Index: 4927995 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.1914. Min Act: -0.1700
Data Index: 4034936 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.1914. Min Act: -0.1700
Data Index: 2716924 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.1914. Min Act: -0.1700
Data Index: 1629016 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5977. Min Range: -6.5977
Max Act: 6.1914. Min Act: -0.1700
Data Index: 8008716 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19