Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2685 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.6467. Min Act: -0.1700
Data Index: 1360116 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.5842. Min Act: -0.1700
Data Index: 2481608 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.4592. Min Act: -0.1700
Data Index: 4389207 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.4592. Min Act: -0.1700
Data Index: 3781833 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.4280. Min Act: -0.1700
Data Index: 211251 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.4280. Min Act: -0.1700
Data Index: 5234945 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.4592. Min Act: -0.1700
Data Index: 894060 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3967. Min Act: -0.1700
Data Index: 739561 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3967. Min Act: -0.1700
Data Index: 2538607 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3967. Min Act: -0.1700
Data Index: 2008856 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3655. Min Act: -0.1700
Data Index: 4878461 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3342. Min Act: -0.1700
Data Index: 2518846 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3030. Min Act: -0.1700
Data Index: 407530 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3030. Min Act: -0.1700
Data Index: 3467930 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.2717. Min Act: -0.1700
Data Index: 6266872 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3030. Min Act: -0.1700
Data Index: 2617184 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3030. Min Act: -0.1700
Data Index: 5937499 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.3030. Min Act: -0.1700
Data Index: 4389205 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.2717. Min Act: -0.1700
Data Index: 215232 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6467. Min Range: -4.6467
Max Act: 4.2717. Min Act: -0.1700
Data Index: 6133634 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19