Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.5018. Min Act: -0.1700
Data Index: 2650477 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.5018. Min Act: -0.1700
Data Index: 6471538 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.5331. Min Act: -0.1700
Data Index: 5451883 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.4081. Min Act: -0.1700
Data Index: 7203747 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3768. Min Act: -0.1700
Data Index: 5592478 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3768. Min Act: -0.1700
Data Index: 3445060 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3456. Min Act: -0.1700
Data Index: 6419810 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3456. Min Act: -0.1700
Data Index: 2656932 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3456. Min Act: -0.1700
Data Index: 7987188 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3143. Min Act: -0.1700
Data Index: 5773550 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3143. Min Act: -0.1700
Data Index: 8525971 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3143. Min Act: -0.1700
Data Index: 2706285 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3143. Min Act: -0.1700
Data Index: 2281653 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.3143. Min Act: -0.1700
Data Index: 5917648 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.2831. Min Act: -0.1700
Data Index: 7377514 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.2831. Min Act: -0.1700
Data Index: 2101357 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.2518. Min Act: -0.1700
Data Index: 4464978 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.2518. Min Act: -0.1700
Data Index: 4735560 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.2831. Min Act: -0.1700
Data Index: 4752903 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5331. Min Range: -5.5331
Max Act: 5.2518. Min Act: -0.1700
Data Index: 8386620 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19