Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.2004. Min Act: -0.1700
Data Index: 8311172 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.1691. Min Act: -0.1700
Data Index: 5852419 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.1379. Min Act: -0.1700
Data Index: 27146 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0754. Min Act: -0.1700
Data Index: 3899433 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0754. Min Act: -0.1700
Data Index: 5971375 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.1066. Min Act: -0.1700
Data Index: 6883686 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0754. Min Act: -0.1700
Data Index: 6062633 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0441. Min Act: -0.1700
Data Index: 245970 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0441. Min Act: -0.1700
Data Index: 5881559 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0441. Min Act: -0.1700
Data Index: 7443636 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2004. Min Range: -5.2004
Max Act: 5.0129. Min Act: -0.1700
Data Index: 8737617 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9816. Min Act: -0.1700
Data Index: 2341960 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9816. Min Act: -0.1700
Data Index: 5699745 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9504. Min Act: -0.1700
Data Index: 5699753 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8879. Min Act: -0.1700
Data Index: 595111 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9191. Min Act: -0.1700
Data Index: 5752285 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9191. Min Act: -0.1700
Data Index: 1224792 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8879. Min Act: -0.1700
Data Index: 4453987 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.9191. Min Act: -0.1700
Data Index: 4992182 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2004. Min Range: -5.2004
Max Act: 4.8879. Min Act: -0.1700
Data Index: 6767785 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19