Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6269 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2069. Min Range: -6.2069
Max Act: 6.2069. Min Act: -0.1700
Data Index: 481137 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.9881. Min Act: -0.1700
Data Index: 6692407 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.8631. Min Act: -0.1700
Data Index: 8227774 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.8319. Min Act: -0.1700
Data Index: 4929786 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.8006. Min Act: -0.1700
Data Index: 1621442 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.7694. Min Act: -0.1700
Data Index: 5984400 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.7381. Min Act: -0.1700
Data Index: 3731042 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.7381. Min Act: -0.1700
Data Index: 6516515 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.7069. Min Act: -0.1700
Data Index: 7824456 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.7069. Min Act: -0.1700
Data Index: 2910954 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.6756. Min Act: -0.1700
Data Index: 7778299 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.6756. Min Act: -0.1700
Data Index: 4008305 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.6444. Min Act: -0.1700
Data Index: 8331906 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.6444. Min Act: -0.1700
Data Index: 3865118 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.6131. Min Act: -0.1700
Data Index: 2443541 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.6131. Min Act: -0.1700
Data Index: 5143678 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.6131. Min Act: -0.1700
Data Index: 5042765 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.5819. Min Act: -0.1700
Data Index: 6675338 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.5819. Min Act: -0.1700
Data Index: 7824458 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2069. Min Range: -6.2069
Max Act: 5.5819. Min Act: -0.1700
Data Index: 7803131 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19