Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6183. Min Range: -8.6183
Max Act: 8.6183. Min Act: -0.1700
Data Index: 5068492 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6183. Min Range: -8.6183
Max Act: 8.4933. Min Act: -0.1700
Data Index: 7635607 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.9308. Min Act: -0.1700
Data Index: 6378085 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.8995. Min Act: -0.1700
Data Index: 8358327 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.8058. Min Act: -0.1700
Data Index: 6560336 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.8058. Min Act: -0.1700
Data Index: 3085865 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.8058. Min Act: -0.1700
Data Index: 4910232 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.7120. Min Act: -0.1700
Data Index: 5342297 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.7433. Min Act: -0.1700
Data Index: 4137926 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.7745. Min Act: -0.1700
Data Index: 4551754 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.7745. Min Act: -0.1700
Data Index: 5096213 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.7120. Min Act: -0.1700
Data Index: 6815997 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.7120. Min Act: -0.1700
Data Index: 3003090 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 8622102 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.6808. Min Act: -0.1700
Data Index: 5061718 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.6495. Min Act: -0.1700
Data Index: 7554617 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.6495. Min Act: -0.1700
Data Index: 169100 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.6183. Min Act: -0.1700
Data Index: 6083947 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.6183. Min Act: -0.1700
Data Index: 6452168 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6183. Min Range: -8.6183
Max Act: 7.6183. Min Act: -0.1700
Data Index: 1757220 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19