Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6118 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.9249. Min Act: -0.1700
Data Index: 3333985 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.9249. Min Act: -0.1700
Data Index: 3441480 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.9249. Min Act: -0.1700
Data Index: 5204368 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.8312. Min Act: -0.1700
Data Index: 4240887 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.7999. Min Act: -0.1700
Data Index: 5874691 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.7687. Min Act: -0.1700
Data Index: 100229 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.7062. Min Act: -0.1700
Data Index: 2897095 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.7374. Min Act: -0.1700
Data Index: 4726601 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.7062. Min Act: -0.1700
Data Index: 7967514 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.7062. Min Act: -0.1700
Data Index: 5882647 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6749. Min Act: -0.1700
Data Index: 7409776 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6749. Min Act: -0.1700
Data Index: 5227884 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6437. Min Act: -0.1700
Data Index: 2699474 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7374877 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6437. Min Act: -0.1700
Data Index: 5886 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6437. Min Act: -0.1700
Data Index: 1212096 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6124. Min Act: -0.1700
Data Index: 24756 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6124. Min Act: -0.1700
Data Index: 1705048 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6124. Min Act: -0.1700
Data Index: 5821668 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9249. Min Range: -6.9249
Max Act: 6.6124. Min Act: -0.1700
Data Index: 6058471 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19