Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.8405. Min Act: -0.1700
Data Index: 3905350 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.6218. Min Act: -0.1700
Data Index: 4627881 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.5593. Min Act: -0.1700
Data Index: 6664605 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.5280. Min Act: -0.1700
Data Index: 7642970 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.5280. Min Act: -0.1700
Data Index: 3536490 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.4655. Min Act: -0.1700
Data Index: 5097945 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.4030. Min Act: -0.1700
Data Index: 1928814 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.4030. Min Act: -0.1700
Data Index: 3517679 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.3718. Min Act: -0.1700
Data Index: 441145 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.3718. Min Act: -0.1700
Data Index: 7629566 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.3405. Min Act: -0.1700
Data Index: 4462092 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.3405. Min Act: -0.1700
Data Index: 778395 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.3093. Min Act: -0.1700
Data Index: 754770 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.2780. Min Act: -0.1700
Data Index: 1807550 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.2780. Min Act: -0.1700
Data Index: 90360 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.2780. Min Act: -0.1700
Data Index: 1982555 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.2780. Min Act: -0.1700
Data Index: 1428754 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.3093. Min Act: -0.1700
Data Index: 7243772 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.2780. Min Act: -0.1700
Data Index: 1706417 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8405. Min Range: -5.8405
Max Act: 5.2468. Min Act: -0.1700
Data Index: 5992308 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19