Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.6831. Min Act: -0.1700
Data Index: 2140520 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.6206. Min Act: -0.1700
Data Index: 23532 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.5268. Min Act: -0.1700
Data Index: 1843972 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.5268. Min Act: -0.1700
Data Index: 4061868 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4956. Min Act: -0.1700
Data Index: 3980768 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.5268. Min Act: -0.1700
Data Index: 2102531 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4956. Min Act: -0.1700
Data Index: 881495 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4956. Min Act: -0.1700
Data Index: 6704215 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4643. Min Act: -0.1700
Data Index: 8154367 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4643. Min Act: -0.1700
Data Index: 4224837 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4643. Min Act: -0.1700
Data Index: 637875 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4331. Min Act: -0.1700
Data Index: 715717 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4643. Min Act: -0.1700
Data Index: 3355140 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4331. Min Act: -0.1700
Data Index: 5938561 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4331. Min Act: -0.1700
Data Index: 2756838 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4018. Min Act: -0.1700
Data Index: 7989784 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4331. Min Act: -0.1700
Data Index: 7428672 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4018. Min Act: -0.1700
Data Index: 3847168 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4018. Min Act: -0.1700
Data Index: 6623768 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6831. Min Range: -6.6831
Max Act: 6.4018. Min Act: -0.1700
Data Index: 8735888 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19