Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1309. Min Range: -7.1309
Max Act: 7.1309. Min Act: -0.1700
Data Index: 7938900 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.7559. Min Act: -0.1700
Data Index: 6590970 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.7246. Min Act: -0.1700
Data Index: 7706384 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.7246. Min Act: -0.1700
Data Index: 5493801 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.7246. Min Act: -0.1700
Data Index: 7753499 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.6621. Min Act: -0.1700
Data Index: 3884960 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.5996. Min Act: -0.1700
Data Index: 432837 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.5684. Min Act: -0.1700
Data Index: 6401074 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.5684. Min Act: -0.1700
Data Index: 6944602 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.5371. Min Act: -0.1700
Data Index: 1456881 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.5059. Min Act: -0.1700
Data Index: 2972214 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.5059. Min Act: -0.1700
Data Index: 1353001 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.4434. Min Act: -0.1700
Data Index: 459125 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.4746. Min Act: -0.1700
Data Index: 3432341 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.4121. Min Act: -0.1700
Data Index: 6446987 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.4121. Min Act: -0.1700
Data Index: 112160 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.4121. Min Act: -0.1700
Data Index: 5190886 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.4121. Min Act: -0.1700
Data Index: 2901463 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.3809. Min Act: -0.1700
Data Index: 2754617 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1309. Min Range: -7.1309
Max Act: 6.3809. Min Act: -0.1700
Data Index: 2471338 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19