Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.3244. Min Act: -0.1700
Data Index: 6771813 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.2773. Min Act: -0.1700
Data Index: 6009404 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.2930. Min Act: -0.1700
Data Index: 3150901 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.2302. Min Act: -0.1700
Data Index: 3448012 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.2145. Min Act: -0.1700
Data Index: 8722630 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1988. Min Act: -0.1700
Data Index: 6775482 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1988. Min Act: -0.1700
Data Index: 2845217 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1830. Min Act: -0.1700
Data Index: 8796386 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1830. Min Act: -0.1700
Data Index: 8484953 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1516. Min Act: -0.1700
Data Index: 191823 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1516. Min Act: -0.1700
Data Index: 7726547 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1358. Min Act: -0.1700
Data Index: 1396388 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1516. Min Act: -0.1700
Data Index: 2670149 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1516. Min Act: -0.1700
Data Index: 5957405 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1516. Min Act: -0.1700
Data Index: 1758093 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1673. Min Act: -0.1700
Data Index: 1563471 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1358. Min Act: -0.1700
Data Index: 6910041 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1358. Min Act: -0.1700
Data Index: 4464632 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1358. Min Act: -0.1700
Data Index: 8627006 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3244. Min Range: -3.3244
Max Act: 3.1358. Min Act: -0.1700
Data Index: 745757 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19