Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1286 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.5902. Min Act: -0.1700
Data Index: 7912840 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.5432. Min Act: -0.1700
Data Index: 5214167 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.4179. Min Act: -0.1700
Data Index: 6221626 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.3708. Min Act: -0.1700
Data Index: 3916033 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.3552. Min Act: -0.1700
Data Index: 6129083 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.3081. Min Act: -0.1700
Data Index: 7172443 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.2924. Min Act: -0.1700
Data Index: 8814891 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.2924. Min Act: -0.1700
Data Index: 791773 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.2295. Min Act: -0.1700
Data Index: 7964412 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1981. Min Act: -0.1700
Data Index: 4457994 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1824. Min Act: -0.1700
Data Index: 6147079 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1981. Min Act: -0.1700
Data Index: 5214166 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1666. Min Act: -0.1700
Data Index: 6204762 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1981. Min Act: -0.1700
Data Index: 6222395 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1509. Min Act: -0.1700
Data Index: 8076873 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1352. Min Act: -0.1700
Data Index: 2303779 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1509. Min Act: -0.1700
Data Index: 4348543 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1509. Min Act: -0.1700
Data Index: 3879818 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1666. Min Act: -0.1700
Data Index: 8023060 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5902. Min Range: -3.5902
Max Act: 3.1194. Min Act: -0.1700
Data Index: 7644672 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19