Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.9669. Min Act: -0.1700
Data Index: 8588351 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.8419. Min Act: -0.1700
Data Index: 6049937 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.6856. Min Act: -0.1700
Data Index: 7067539 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.6231. Min Act: -0.1700
Data Index: 345486 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.5606. Min Act: -0.1700
Data Index: 4762099 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.5294. Min Act: -0.1700
Data Index: 5998243 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.4981. Min Act: -0.1700
Data Index: 1131907 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.5294. Min Act: -0.1700
Data Index: 5019346 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.4981. Min Act: -0.1700
Data Index: 5948819 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.4044. Min Act: -0.1700
Data Index: 2235244 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.4044. Min Act: -0.1700
Data Index: 1088692 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3731. Min Act: -0.1700
Data Index: 5636002 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.4044. Min Act: -0.1700
Data Index: 3418328 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3731. Min Act: -0.1700
Data Index: 7385129 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3731. Min Act: -0.1700
Data Index: 5865034 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3419. Min Act: -0.1700
Data Index: 4875286 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3419. Min Act: -0.1700
Data Index: 3889444 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3419. Min Act: -0.1700
Data Index: 2590724 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3106. Min Act: -0.1700
Data Index: 7146280 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9669. Min Range: -6.9669
Max Act: 6.3106. Min Act: -0.1700
Data Index: 1571577 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19