Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.4500. Min Act: -0.1700
Data Index: 1792931 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.4187. Min Act: -0.1700
Data Index: 8269937 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.3250. Min Act: -0.1700
Data Index: 7156200 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.2312. Min Act: -0.1700
Data Index: 3791557 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.1062. Min Act: -0.1700
Data Index: 8681899 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.0437. Min Act: -0.1700
Data Index: 5311736 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.0125. Min Act: -0.1700
Data Index: 471683 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4500. Min Range: -6.4500
Max Act: 6.0125. Min Act: -0.1700
Data Index: 4714574 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.9812. Min Act: -0.1700
Data Index: 2409545 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.9812. Min Act: -0.1700
Data Index: 2731599 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.9812. Min Act: -0.1700
Data Index: 6222416 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.9500. Min Act: -0.1700
Data Index: 601152 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.9812. Min Act: -0.1700
Data Index: 3632466 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.9500. Min Act: -0.1700
Data Index: 7964638 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.9187. Min Act: -0.1700
Data Index: 7747989 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.8875. Min Act: -0.1700
Data Index: 3399941 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.8875. Min Act: -0.1700
Data Index: 133371 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.8875. Min Act: -0.1700
Data Index: 2424133 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.8875. Min Act: -0.1700
Data Index: 6795065 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4500. Min Range: -6.4500
Max Act: 5.8875. Min Act: -0.1700
Data Index: 2128599 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19