Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1592. Min Range: -4.1592
Max Act: 4.1592. Min Act: -0.1700
Data Index: 7337512 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1592. Min Range: -4.1592
Max Act: 4.0342. Min Act: -0.1700
Data Index: 4294392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1592. Min Range: -4.1592
Max Act: 4.0029. Min Act: -0.1700
Data Index: 4021460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1592. Min Range: -4.1592
Max Act: 4.0029. Min Act: -0.1607
Data Index: 5824836 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1592. Min Range: -4.1592
Max Act: 4.0029. Min Act: -0.1639
Data Index: 5824837 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9716. Min Act: -0.1700
Data Index: 6534968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9716. Min Act: -0.1700
Data Index: 7582426 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9716. Min Act: -0.1700
Data Index: 3489505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9716. Min Act: -0.1700
Data Index: 1288298 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9716. Min Act: -0.1700
Data Index: 6620407 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9716. Min Act: -0.1700
Data Index: 1370035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9716. Min Act: -0.1700
Data Index: 2357545 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1700
Data Index: 1493071 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1700
Data Index: 779496 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1700
Data Index: 1053252 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1700
Data Index: 655239 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1699
Data Index: 815719 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1700
Data Index: 39667 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1700
Data Index: 876388 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1592. Min Range: -4.1592
Max Act: 3.9404. Min Act: -0.1700
Data Index: 11982 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19