Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.4279. Min Act: -0.1700
Data Index: 8321120 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.3966. Min Act: -0.1700
Data Index: 8049237 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.3341. Min Act: -0.1700
Data Index: 1493547 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.2716. Min Act: -0.1700
Data Index: 2357050 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.2716. Min Act: -0.1700
Data Index: 5322782 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1779. Min Act: -0.1700
Data Index: 3784082 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.2091. Min Act: -0.1700
Data Index: 4265353 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.2091. Min Act: -0.1700
Data Index: 2440303 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1779. Min Act: -0.1700
Data Index: 7089605 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1466. Min Act: -0.1700
Data Index: 5682735 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1466. Min Act: -0.1700
Data Index: 5056691 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1779. Min Act: -0.1700
Data Index: 2383301 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1466. Min Act: -0.1700
Data Index: 169057 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1154. Min Act: -0.1700
Data Index: 1949134 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.1154. Min Act: -0.1700
Data Index: 6092296 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.0216. Min Act: -0.1700
Data Index: 3571563 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.0216. Min Act: -0.1700
Data Index: 5894686 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4279. Min Range: -7.4279
Max Act: 7.0216. Min Act: -0.1700
Data Index: 6231958 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4279. Min Range: -7.4279
Max Act: 6.9591. Min Act: -0.1700
Data Index: 3542513 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4279. Min Range: -7.4279
Max Act: 6.9904. Min Act: -0.1700
Data Index: 4306699 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19