Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1472 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.8038. Min Act: -0.1700
Data Index: 6109623 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.3811. Min Act: -0.1700
Data Index: 2070893 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.3498. Min Act: -0.1700
Data Index: 2548081 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.3341. Min Act: -0.1700
Data Index: 2624077 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.2556. Min Act: -0.1700
Data Index: 8312532 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.2084. Min Act: -0.1700
Data Index: 3344520 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1927. Min Act: -0.1700
Data Index: 8751644 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1927. Min Act: -0.1700
Data Index: 4320514 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1770. Min Act: -0.1700
Data Index: 6299128 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1770. Min Act: -0.1700
Data Index: 5774970 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1770. Min Act: -0.1700
Data Index: 455914 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1612. Min Act: -0.1700
Data Index: 1287591 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1612. Min Act: -0.1700
Data Index: 3759941 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1612. Min Act: -0.1700
Data Index: 4234184 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1455. Min Act: -0.1700
Data Index: 7155829 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.0982. Min Act: -0.1700
Data Index: 5289727 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1140. Min Act: -0.1700
Data Index: 6724501 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1297. Min Act: -0.1700
Data Index: 7431669 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.1297. Min Act: -0.1700
Data Index: 5096442 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8038. Min Range: -3.8038
Max Act: 3.0825. Min Act: -0.1700
Data Index: 8678456 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19