Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 593 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0518. Min Range: -5.0518
Max Act: 5.0206. Min Act: -0.1700
Data Index: 3703367 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0518. Min Range: -5.0518
Max Act: 5.0518. Min Act: -0.1700
Data Index: 6616443 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.9893. Min Act: -0.1700
Data Index: 5730899 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.9581. Min Act: -0.1700
Data Index: 1575656 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.9893. Min Act: -0.1700
Data Index: 5148950 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8643. Min Act: -0.1700
Data Index: 8151770 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8956. Min Act: -0.1700
Data Index: 5498112 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 5037857 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 3529303 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8643. Min Act: -0.1700
Data Index: 5581404 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 7859694 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8643. Min Act: -0.1700
Data Index: 2129804 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 1447840 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 7620523 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 8215833 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 3095788 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8331. Min Act: -0.1700
Data Index: 3854768 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8018. Min Act: -0.1700
Data Index: 8175858 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.8018. Min Act: -0.1700
Data Index: 6866734 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0518. Min Range: -5.0518
Max Act: 4.7706. Min Act: -0.1700
Data Index: 6440531 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19