Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.4350. Min Act: -0.1700
Data Index: 6335168 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3725. Min Act: -0.1700
Data Index: 6787675 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3725. Min Act: -0.1700
Data Index: 6335904 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.3099. Min Act: -0.1700
Data Index: 207592 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2787. Min Act: -0.1700
Data Index: 2745533 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2787. Min Act: -0.1700
Data Index: 6257244 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2787. Min Act: -0.1700
Data Index: 2288508 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2474. Min Act: -0.1700
Data Index: 4002247 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2474. Min Act: -0.1700
Data Index: 6055889 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2162. Min Act: -0.1700
Data Index: 4392055 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2474. Min Act: -0.1700
Data Index: 3815041 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2162. Min Act: -0.1700
Data Index: 7958091 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2162. Min Act: -0.1700
Data Index: 6376167 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.2474. Min Act: -0.1700
Data Index: 7615019 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1849. Min Act: -0.1700
Data Index: 6328504 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1849. Min Act: -0.1700
Data Index: 148134 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1537. Min Act: -0.1700
Data Index: 1340661 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1849. Min Act: -0.1700
Data Index: 6538122 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1849. Min Act: -0.1700
Data Index: 6595473 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4350. Min Range: -4.4350
Max Act: 4.1849. Min Act: -0.1700
Data Index: 394009 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19