Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5787 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.8856. Min Act: -0.1700
Data Index: 6231234 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.7294. Min Act: -0.1700
Data Index: 8809589 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.7606. Min Act: -0.1700
Data Index: 6231233 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.6044. Min Act: -0.1700
Data Index: 2730400 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.5731. Min Act: -0.1700
Data Index: 4013645 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.5106. Min Act: -0.1700
Data Index: 3225226 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.5106. Min Act: -0.1700
Data Index: 7049074 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.5106. Min Act: -0.1700
Data Index: 448718 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.4794. Min Act: -0.1700
Data Index: 5713020 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.4481. Min Act: -0.1700
Data Index: 3190677 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.4169. Min Act: -0.1700
Data Index: 2364444 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.4169. Min Act: -0.1700
Data Index: 5533076 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.4169. Min Act: -0.1700
Data Index: 3077495 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.3856. Min Act: -0.1700
Data Index: 998709 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.3856. Min Act: -0.1700
Data Index: 3783927 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.3231. Min Act: -0.1700
Data Index: 6969185 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.2606. Min Act: -0.1700
Data Index: 5727123 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.2606. Min Act: -0.1700
Data Index: 2504187 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.2606. Min Act: -0.1700
Data Index: 8222943 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8856. Min Range: -7.8856
Max Act: 7.2606. Min Act: -0.1700
Data Index: 2873291 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19