Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0581. Min Range: -3.0581
Max Act: 3.0581. Min Act: -0.1700
Data Index: 5988290 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0581. Min Range: -3.0581
Max Act: 3.0108. Min Act: -0.1700
Data Index: 1418911 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9792. Min Act: -0.1700
Data Index: 6391170 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9792. Min Act: -0.1700
Data Index: 3641277 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0581. Min Range: -3.0581
Max Act: 3.0108. Min Act: -0.1700
Data Index: 7560461 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9634. Min Act: -0.1700
Data Index: 7039169 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9475. Min Act: -0.1700
Data Index: 2842763 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9158. Min Act: -0.1700
Data Index: 1818901 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9317. Min Act: -0.1700
Data Index: 1330390 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9475. Min Act: -0.1700
Data Index: 4180732 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9475. Min Act: -0.1700
Data Index: 6243736 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9317. Min Act: -0.1700
Data Index: 3361573 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9634. Min Act: -0.1700
Data Index: 3541065 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.8841. Min Act: -0.1700
Data Index: 7830770 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9000. Min Act: -0.1700
Data Index: 966744 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.8683. Min Act: -0.1700
Data Index: 8087295 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.8206. Min Act: -0.1700
Data Index: 4520521 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.9000. Min Act: -0.1700
Data Index: 6897135 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.8841. Min Act: -0.1700
Data Index: 100333 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0581. Min Range: -3.0581
Max Act: 2.8206. Min Act: -0.1700
Data Index: 3063579 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19