Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.5186. Min Act: -0.1700
Data Index: 2705780 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4716. Min Act: -0.1700
Data Index: 8355053 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4403. Min Act: -0.1700
Data Index: 6282582 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4403. Min Act: -0.1700
Data Index: 4441257 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4403. Min Act: -0.1700
Data Index: 346083 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4403. Min Act: -0.1700
Data Index: 5523547 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4246. Min Act: -0.1700
Data Index: 1659766 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4089. Min Act: -0.1700
Data Index: 6588228 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.4089. Min Act: -0.1700
Data Index: 697535 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3933. Min Act: -0.1700
Data Index: 5673462 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3776. Min Act: -0.1700
Data Index: 1197611 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3933. Min Act: -0.1700
Data Index: 4759031 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3776. Min Act: -0.1700
Data Index: 4738192 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3933. Min Act: -0.1700
Data Index: 5523546 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3776. Min Act: -0.1700
Data Index: 6580118 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3619. Min Act: -0.1700
Data Index: 369607 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3776. Min Act: -0.1700
Data Index: 4650557 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3619. Min Act: -0.1700
Data Index: 4703349 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3776. Min Act: -0.1700
Data Index: 6286916 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5186. Min Range: -3.5186
Max Act: 3.3776. Min Act: -0.1700
Data Index: 1758894 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19