Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.5186. Min Act: -0.1700
Data Index: 1328630 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.4862. Min Act: -0.1700
Data Index: 1898756 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.5024. Min Act: -0.1700
Data Index: 4131875 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.4375. Min Act: -0.1700
Data Index: 8199862 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.4375. Min Act: -0.1700
Data Index: 3517506 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.3886. Min Act: -0.1700
Data Index: 1929880 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.3886. Min Act: -0.1700
Data Index: 2970039 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.3559. Min Act: -0.1700
Data Index: 2253193 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.3722. Min Act: -0.1700
Data Index: 4871354 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.3559. Min Act: -0.1700
Data Index: 5402483 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.3066. Min Act: -0.1700
Data Index: 5981634 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.2902. Min Act: -0.1700
Data Index: 6155087 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.2902. Min Act: -0.1700
Data Index: 3696498 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.2572. Min Act: -0.1700
Data Index: 5312189 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.2737. Min Act: -0.1700
Data Index: 8658684 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.2572. Min Act: -0.1700
Data Index: 5198291 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.2241. Min Act: -0.1700
Data Index: 1889919 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.1910. Min Act: -0.1700
Data Index: 8622406 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.1910. Min Act: -0.1700
Data Index: 442674 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5186. Min Range: -2.5186
Max Act: 2.1910. Min Act: -0.1700
Data Index: 500709 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19