Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.6615. Min Act: -0.1700
Data Index: 1056289 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.6615. Min Act: -0.1700
Data Index: 6261586 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.6615. Min Act: -0.1700
Data Index: 462912 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.6615. Min Act: -0.1700
Data Index: 235140 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5990. Min Act: -0.1700
Data Index: 3070628 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.6302. Min Act: -0.1700
Data Index: 6558219 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.6302. Min Act: -0.1700
Data Index: 57352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5990. Min Act: -0.1700
Data Index: 5518144 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5677. Min Act: -0.1700
Data Index: 7933659 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5990. Min Act: -0.1700
Data Index: 837134 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5990. Min Act: -0.1700
Data Index: 446145 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5990. Min Act: -0.1700
Data Index: 5761423 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5677. Min Act: -0.1700
Data Index: 1913303 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5677. Min Act: -0.1700
Data Index: 7562570 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5677. Min Act: -0.1700
Data Index: 4830396 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5990. Min Act: -0.1700
Data Index: 8651321 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5365. Min Act: -0.1700
Data Index: 4638585 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5677. Min Act: -0.1700
Data Index: 53142 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5365. Min Act: -0.1700
Data Index: 6526915 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6615. Min Range: -4.6615
Max Act: 4.5365. Min Act: -0.1700
Data Index: 856462 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19