Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1363 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.3609. Min Act: -0.1700
Data Index: 2004702 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 1094209 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 1089543 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 4313838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 3267617 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 2106997 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2984. Min Act: -0.1700
Data Index: 513545 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 8645074 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2671. Min Act: -0.1700
Data Index: 2815042 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 4646587 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 3154383 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 2455186 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 7849769 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 7780397 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 7224248 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2359. Min Act: -0.1700
Data Index: 4767659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.1734. Min Act: -0.1700
Data Index: 221799 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.1734. Min Act: -0.1700
Data Index: 712451 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.2046. Min Act: -0.1700
Data Index: 184626 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3609. Min Range: -6.3609
Max Act: 6.1734. Min Act: -0.1700
Data Index: 4414535 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19