Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1075 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.6656. Min Act: -0.1700
Data Index: 4342125 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.3844. Min Act: -0.1700
Data Index: 928653 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.3219. Min Act: -0.1700
Data Index: 2047505 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.2281. Min Act: -0.1700
Data Index: 2750020 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1969. Min Act: -0.1700
Data Index: 1509790 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1969. Min Act: -0.1700
Data Index: 2211280 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1969. Min Act: -0.1700
Data Index: 6618071 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1656. Min Act: -0.1700
Data Index: 4415559 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1656. Min Act: -0.1700
Data Index: 7326515 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1344. Min Act: -0.1700
Data Index: 8095094 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1344. Min Act: -0.1700
Data Index: 6910799 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1344. Min Act: -0.1700
Data Index: 85856 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1656. Min Act: -0.1700
Data Index: 3358808 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.1031. Min Act: -0.1700
Data Index: 8214197 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.0719. Min Act: -0.1700
Data Index: 3252224 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.0406. Min Act: -0.1700
Data Index: 1221550 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.0719. Min Act: -0.1700
Data Index: 814940 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.0406. Min Act: -0.1700
Data Index: 7363906 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.0406. Min Act: -0.1700
Data Index: 6771087 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6656. Min Range: -6.6656
Max Act: 6.0094. Min Act: -0.1700
Data Index: 4069196 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19