Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1005. Min Range: -2.1005
Max Act: 2.1005. Min Act: -0.1700
Data Index: 485806 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9996. Min Act: -0.1651
Data Index: 2594173 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9742. Min Act: -0.1697
Data Index: 2824290 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9742. Min Act: -0.1700
Data Index: 3158096 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9488. Min Act: -0.1698
Data Index: 7875890 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9318. Min Act: -0.1685
Data Index: 7748402 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9403. Min Act: -0.1685
Data Index: 3390503 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9403. Min Act: -0.1664
Data Index: 2542213 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9403. Min Act: -0.1574
Data Index: 2099062 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9147. Min Act: -0.1691
Data Index: 1324530 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9233. Min Act: -0.1672
Data Index: 6434454 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.9233. Min Act: -0.1699
Data Index: 6578380 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8977. Min Act: -0.1698
Data Index: 7988743 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8977. Min Act: -0.1697
Data Index: 1554038 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8977. Min Act: -0.1697
Data Index: 905124 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8892. Min Act: -0.1639
Data Index: 6561092 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8892. Min Act: -0.1698
Data Index: 6289194 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8892. Min Act: -0.1696
Data Index: 1058496 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8892. Min Act: -0.1668
Data Index: 2138849 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1005. Min Range: -2.1005
Max Act: 1.8806. Min Act: -0.1700
Data Index: 5167602 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19