Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2922 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2152. Min Range: -7.2152
Max Act: 7.2152. Min Act: -0.1700
Data Index: 344149 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.8402. Min Act: -0.1700
Data Index: 3458812 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.8089. Min Act: -0.1700
Data Index: 8509179 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.7152. Min Act: -0.1700
Data Index: 3540670 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.7464. Min Act: -0.1700
Data Index: 5202365 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.7152. Min Act: -0.1700
Data Index: 5769067 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.6839. Min Act: -0.1700
Data Index: 5432217 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5902. Min Act: -0.1700
Data Index: 5824550 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5902. Min Act: -0.1700
Data Index: 298028 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.6214. Min Act: -0.1700
Data Index: 8419861 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5902. Min Act: -0.1700
Data Index: 5604369 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5589. Min Act: -0.1700
Data Index: 5939853 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5902. Min Act: -0.1700
Data Index: 3050008 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5902. Min Act: -0.1700
Data Index: 8650750 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5902. Min Act: -0.1700
Data Index: 2698140 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5902. Min Act: -0.1700
Data Index: 1353356 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5589. Min Act: -0.1700
Data Index: 1571346 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5589. Min Act: -0.1700
Data Index: 7509173 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5589. Min Act: -0.1700
Data Index: 6066377 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2152. Min Range: -7.2152
Max Act: 6.5589. Min Act: -0.1700
Data Index: 5270358 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19