Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0844. Min Range: -8.0844
Max Act: 8.0844. Min Act: -0.1700
Data Index: 7411920 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.8969. Min Act: -0.1700
Data Index: 6278397 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.8969. Min Act: -0.1700
Data Index: 6287337 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.8969. Min Act: -0.1700
Data Index: 1022917 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.8969. Min Act: -0.1700
Data Index: 2958609 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 8644026 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7719. Min Act: -0.1700
Data Index: 3522783 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7719. Min Act: -0.1700
Data Index: 1044738 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7719. Min Act: -0.1700
Data Index: 5779826 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7719. Min Act: -0.1700
Data Index: 6069279 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 317225 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 576523 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 1109996 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 8427403 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 8070265 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 964511 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.6469. Min Act: -0.1700
Data Index: 2490790 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.6469. Min Act: -0.1700
Data Index: 1318990 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.6469. Min Act: -0.1700
Data Index: 7198724 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0844. Min Range: -8.0844
Max Act: 7.6156. Min Act: -0.1700
Data Index: 5741163 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19