Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.4896. Min Act: -0.1700
Data Index: 544040 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.4426. Min Act: -0.1700
Data Index: 2629440 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.3799. Min Act: -0.1700
Data Index: 1281732 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.3799. Min Act: -0.1700
Data Index: 227539 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.3485. Min Act: -0.1700
Data Index: 5315518 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.3485. Min Act: -0.1700
Data Index: 3287534 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.3171. Min Act: -0.1700
Data Index: 8610831 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2700. Min Act: -0.1700
Data Index: 3890677 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2543. Min Act: -0.1700
Data Index: 1085682 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2700. Min Act: -0.1700
Data Index: 3184556 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2072. Min Act: -0.1700
Data Index: 6089162 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2543. Min Act: -0.1700
Data Index: 3562774 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2072. Min Act: -0.1700
Data Index: 458319 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2072. Min Act: -0.1700
Data Index: 7944017 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2229. Min Act: -0.1700
Data Index: 8214198 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.1914. Min Act: -0.1700
Data Index: 2491822 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.2072. Min Act: -0.1700
Data Index: 3303970 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.1757. Min Act: -0.1700
Data Index: 8480493 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.1600. Min Act: -0.1700
Data Index: 4344452 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4896. Min Range: -3.4896
Max Act: 3.1757. Min Act: -0.1700
Data Index: 8051834 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19