Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2717. Min Range: -8.2717
Max Act: 8.2717. Min Act: -0.1696
Data Index: 1658743 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2717. Min Range: -8.2717
Max Act: 8.0842. Min Act: -0.1700
Data Index: 5091360 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.8967. Min Act: -0.1700
Data Index: 423048 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.8342. Min Act: -0.1700
Data Index: 1055389 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.7717. Min Act: -0.1700
Data Index: 7566627 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.7717. Min Act: -0.1700
Data Index: 3955152 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.6467. Min Act: -0.1700
Data Index: 2975571 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.6467. Min Act: -0.1700
Data Index: 649193 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.5842. Min Act: -0.1700
Data Index: 5271150 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.5842. Min Act: -0.1700
Data Index: 8117018 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.5217. Min Act: -0.1700
Data Index: 3758180 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.5217. Min Act: -0.1700
Data Index: 8197478 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.4592. Min Act: -0.1700
Data Index: 2286220 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.4592. Min Act: -0.1683
Data Index: 7861666 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.3967. Min Act: -0.1699
Data Index: 747698 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.4592. Min Act: -0.1700
Data Index: 5627018 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.4592. Min Act: -0.1700
Data Index: 7203434 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.3967. Min Act: -0.1700
Data Index: 3961157 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.3342. Min Act: -0.1700
Data Index: 7995026 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2717. Min Range: -8.2717
Max Act: 7.3030. Min Act: -0.1700
Data Index: 3065622 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19