Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5634 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0583. Min Range: -10.0583
Max Act: 10.0583. Min Act: -0.1700
Data Index: 2982455 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.8708. Min Act: -0.1700
Data Index: 889117 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.6833. Min Act: -0.1700
Data Index: 6756150 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.6833. Min Act: -0.1700
Data Index: 796227 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.6208. Min Act: -0.1700
Data Index: 5793158 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.6833. Min Act: -0.1700
Data Index: 1529147 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.5583. Min Act: -0.1700
Data Index: 6549592 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.5583. Min Act: -0.1700
Data Index: 7528187 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.4958. Min Act: -0.1700
Data Index: 2153581 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.3708. Min Act: -0.1700
Data Index: 1267020 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.3083. Min Act: -0.1700
Data Index: 7151937 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 5468 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.3083. Min Act: -0.1700
Data Index: 1222875 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.3083. Min Act: -0.1700
Data Index: 4917051 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 1329917 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 8203542 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 2731379 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 7291507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 1225694 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0583. Min Range: -10.0583
Max Act: 9.2458. Min Act: -0.1700
Data Index: 5294414 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19