Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0447. Min Range: -3.0447
Max Act: 3.0447. Min Act: -0.1700
Data Index: 2420980 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0447. Min Range: -3.0447
Max Act: 3.0289. Min Act: -0.1700
Data Index: 4890341 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0447. Min Range: -3.0447
Max Act: 3.0131. Min Act: -0.1700
Data Index: 3059257 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0447. Min Range: -3.0447
Max Act: 3.0131. Min Act: -0.1700
Data Index: 255536 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0447. Min Range: -3.0447
Max Act: 3.0131. Min Act: -0.1700
Data Index: 5197472 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0447. Min Range: -3.0447
Max Act: 3.0131. Min Act: -0.1700
Data Index: 3549783 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9973. Min Act: -0.1700
Data Index: 4420347 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9973. Min Act: -0.1700
Data Index: 8165992 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9973. Min Act: -0.1700
Data Index: 4112195 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9973. Min Act: -0.1700
Data Index: 5580813 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0447. Min Range: -3.0447
Max Act: 3.0131. Min Act: -0.1700
Data Index: 3882999 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9973. Min Act: -0.1700
Data Index: 3483670 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9815. Min Act: -0.1700
Data Index: 3501760 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9815. Min Act: -0.1700
Data Index: 539940 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9815. Min Act: -0.1700
Data Index: 1138129 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9973. Min Act: -0.1700
Data Index: 1545744 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9815. Min Act: -0.1700
Data Index: 1531463 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9815. Min Act: -0.1700
Data Index: 7471686 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9973. Min Act: -0.1700
Data Index: 4216165 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0447. Min Range: -3.0447
Max Act: 2.9815. Min Act: -0.1700
Data Index: 4738752 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19