Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 831 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5831. Min Range: -6.5831
Max Act: 6.5831. Min Act: -0.1700
Data Index: 2524183 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5831. Min Range: -6.5831
Max Act: 6.4268. Min Act: -0.1700
Data Index: 7646260 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5831. Min Range: -6.5831
Max Act: 6.2706. Min Act: -0.1700
Data Index: 1296380 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5831. Min Range: -6.5831
Max Act: 6.2393. Min Act: -0.1700
Data Index: 3403577 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.9268. Min Act: -0.1700
Data Index: 2450089 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.9268. Min Act: -0.1700
Data Index: 3319327 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8956. Min Act: -0.1700
Data Index: 2077995 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8956. Min Act: -0.1700
Data Index: 801770 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8956. Min Act: -0.1700
Data Index: 5786375 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8643. Min Act: -0.1700
Data Index: 6568334 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8643. Min Act: -0.1700
Data Index: 3972784 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8643. Min Act: -0.1700
Data Index: 1242144 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8643. Min Act: -0.1700
Data Index: 4301800 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8643. Min Act: -0.1700
Data Index: 2741406 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8331. Min Act: -0.1700
Data Index: 4729340 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8331. Min Act: -0.1700
Data Index: 8740406 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8643. Min Act: -0.1700
Data Index: 8177485 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8331. Min Act: -0.1700
Data Index: 7976074 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8018. Min Act: -0.1700
Data Index: 102574 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5831. Min Range: -6.5831
Max Act: 5.8018. Min Act: -0.1700
Data Index: 2372157 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19