Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4681 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2700. Min Range: -6.2700
Max Act: 6.2700. Min Act: -0.1700
Data Index: 4934090 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2700. Min Range: -6.2700
Max Act: 6.2075. Min Act: -0.1700
Data Index: 5547550 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2700. Min Range: -6.2700
Max Act: 6.2075. Min Act: -0.1700
Data Index: 4035984 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2700. Min Range: -6.2700
Max Act: 6.0512. Min Act: -0.1700
Data Index: 5657704 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2700. Min Range: -6.2700
Max Act: 6.0200. Min Act: -0.1700
Data Index: 613052 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.9887. Min Act: -0.1700
Data Index: 2486009 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.9575. Min Act: -0.1699
Data Index: 3500001 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.9262. Min Act: -0.1700
Data Index: 7408999 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.9262. Min Act: -0.1700
Data Index: 3632890 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.9262. Min Act: -0.1700
Data Index: 2714422 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8950. Min Act: -0.1700
Data Index: 2251579 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8950. Min Act: -0.1700
Data Index: 5211695 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8950. Min Act: -0.1700
Data Index: 2211866 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8950. Min Act: -0.1700
Data Index: 2141501 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8950. Min Act: -0.1700
Data Index: 1833305 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8637. Min Act: -0.1700
Data Index: 1891547 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8950. Min Act: -0.1700
Data Index: 5561745 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8637. Min Act: -0.1700
Data Index: 2230150 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8637. Min Act: -0.1700
Data Index: 1875925 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2700. Min Range: -6.2700
Max Act: 5.8637. Min Act: -0.1700
Data Index: 114982 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19