Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0282. Min Range: -7.0282
Max Act: 7.0282. Min Act: -0.1700
Data Index: 141392 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.4970. Min Act: -0.1700
Data Index: 6688834 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.2782. Min Act: -0.1700
Data Index: 7212446 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.2470. Min Act: -0.1700
Data Index: 166157 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.2782. Min Act: -0.1700
Data Index: 1363158 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.2157. Min Act: -0.1700
Data Index: 5899249 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.2157. Min Act: -0.1700
Data Index: 2542636 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.1845. Min Act: -0.1700
Data Index: 330219 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.1532. Min Act: -0.1700
Data Index: 7607003 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.1220. Min Act: -0.1700
Data Index: 439129 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.1220. Min Act: -0.1700
Data Index: 3017851 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0907. Min Act: -0.1700
Data Index: 6571634 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0907. Min Act: -0.1700
Data Index: 8135024 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.1220. Min Act: -0.1700
Data Index: 7821486 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0907. Min Act: -0.1700
Data Index: 5601131 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0595. Min Act: -0.1700
Data Index: 1470584 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0595. Min Act: -0.1700
Data Index: 2477855 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0595. Min Act: -0.1700
Data Index: 3124004 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0282. Min Act: -0.1700
Data Index: 5060669 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0282. Min Range: -7.0282
Max Act: 6.0282. Min Act: -0.1700
Data Index: 3863628 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19