Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.3722. Min Act: -0.1700
Data Index: 2896800 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.3097. Min Act: -0.1700
Data Index: 256760 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.2785. Min Act: -0.1700
Data Index: 542044 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.2160. Min Act: -0.1700
Data Index: 4628693 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.1847. Min Act: -0.1700
Data Index: 5301489 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.1222. Min Act: -0.1700
Data Index: 3045098 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.1222. Min Act: -0.1700
Data Index: 8489072 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.1222. Min Act: -0.1700
Data Index: 7558468 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0910. Min Act: -0.1700
Data Index: 5819764 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.1222. Min Act: -0.1700
Data Index: 1575776 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0910. Min Act: -0.1700
Data Index: 542043 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0910. Min Act: -0.1700
Data Index: 2843061 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0597. Min Act: -0.1700
Data Index: 2622012 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0597. Min Act: -0.1700
Data Index: 5213255 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0597. Min Act: -0.1700
Data Index: 6509480 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0285. Min Act: -0.1700
Data Index: 971719 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3722. Min Range: -5.3722
Max Act: 5.0285. Min Act: -0.1700
Data Index: 2843059 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3722. Min Range: -5.3722
Max Act: 4.9972. Min Act: -0.1700
Data Index: 7593334 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3722. Min Range: -5.3722
Max Act: 4.9972. Min Act: -0.1700
Data Index: 6485143 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3722. Min Range: -5.3722
Max Act: 4.9972. Min Act: -0.1700
Data Index: 5109127 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19