Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3455 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.5625. Min Act: -0.1700
Data Index: 4206645 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.3750. Min Act: -0.1700
Data Index: 7350280 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.3125. Min Act: -0.1700
Data Index: 4829839 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.1875. Min Act: -0.1700
Data Index: 1407490 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.1562. Min Act: -0.1700
Data Index: 5952110 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.1250. Min Act: -0.1700
Data Index: 5938631 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.0937. Min Act: -0.1700
Data Index: 3234471 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.1250. Min Act: -0.1700
Data Index: 8766629 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.0625. Min Act: -0.1700
Data Index: 5708623 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.0312. Min Act: -0.1700
Data Index: 7547767 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.0312. Min Act: -0.1700
Data Index: 2425207 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.0312. Min Act: -0.1700
Data Index: 1223980 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.0312. Min Act: -0.1700
Data Index: 13417 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5625. Min Range: -5.5625
Max Act: 5.0000. Min Act: -0.1700
Data Index: 7824265 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5625. Min Range: -5.5625
Max Act: 4.9687. Min Act: -0.1700
Data Index: 8551910 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5625. Min Range: -5.5625
Max Act: 4.9687. Min Act: -0.1700
Data Index: 4667506 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5625. Min Range: -5.5625
Max Act: 4.9062. Min Act: -0.1700
Data Index: 8824449 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5625. Min Range: -5.5625
Max Act: 4.9375. Min Act: -0.1700
Data Index: 668315 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5625. Min Range: -5.5625
Max Act: 4.9062. Min Act: -0.1700
Data Index: 5769793 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5625. Min Range: -5.5625
Max Act: 4.9062. Min Act: -0.1700
Data Index: 4693036 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19