Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0750. Min Range: -5.0750
Max Act: 5.0750. Min Act: -0.1700
Data Index: 6120872 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0750. Min Range: -5.0750
Max Act: 5.0438. Min Act: -0.1700
Data Index: 6855993 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0750. Min Range: -5.0750
Max Act: 5.0438. Min Act: -0.1700
Data Index: 3085159 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.9188. Min Act: -0.1700
Data Index: 8597264 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.9500. Min Act: -0.1700
Data Index: 2830129 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.9188. Min Act: -0.1700
Data Index: 3260608 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.9188. Min Act: -0.1700
Data Index: 5643976 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.9188. Min Act: -0.1700
Data Index: 2894217 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.9188. Min Act: -0.1700
Data Index: 4014396 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8875. Min Act: -0.1700
Data Index: 6489807 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8875. Min Act: -0.1700
Data Index: 6670615 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8875. Min Act: -0.1700
Data Index: 3491689 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8875. Min Act: -0.1700
Data Index: 3125201 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8875. Min Act: -0.1700
Data Index: 5631113 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8563. Min Act: -0.1700
Data Index: 7096008 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8250. Min Act: -0.1700
Data Index: 1916788 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8250. Min Act: -0.1700
Data Index: 3125206 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.8250. Min Act: -0.1700
Data Index: 1173460 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.7938. Min Act: -0.1700
Data Index: 2387615 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0750. Min Range: -5.0750
Max Act: 4.7938. Min Act: -0.1700
Data Index: 6707095 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19