Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2887 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2456. Min Act: -0.1700
Data Index: 4743926 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2456. Min Act: -0.1700
Data Index: 5529755 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.2143. Min Act: -0.1700
Data Index: 5560722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1206. Min Act: -0.1700
Data Index: 4768535 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1518. Min Act: -0.1700
Data Index: 8408441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1206. Min Act: -0.1700
Data Index: 7435480 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.1206. Min Act: -0.1700
Data Index: 4470290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0893. Min Act: -0.1700
Data Index: 7458578 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0893. Min Act: -0.1700
Data Index: 7329259 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0893. Min Act: -0.1700
Data Index: 4591584 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 1658011 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 8305977 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 4481875 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 1082013 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 6501016 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 5349163 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 1468045 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 5284903 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 821587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2456. Min Range: -4.2456
Max Act: 4.0581. Min Act: -0.1700
Data Index: 6657585 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19