Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1700
Data Index: 6184800 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1686
Data Index: 5421708 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1637
Data Index: 5323440 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1684
Data Index: 5184554 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1534
Data Index: 8468244 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1613
Data Index: 4605965 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1700
Data Index: 8022014 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1696
Data Index: 7471299 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1534
Data Index: 3851480 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1640
Data Index: 241794 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1681
Data Index: 3779709 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1700
Data Index: 6778121 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1700
Data Index: 6217134 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1534
Data Index: 2594750 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1700
Data Index: 1794646 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1627
Data Index: 1161042 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5116. Min Act: -0.1699
Data Index: 842195 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.5191. Min Act: -0.1693
Data Index: 2373910 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.4890. Min Act: -0.1700
Data Index: 5501038 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5191. Min Range: -0.5191
Max Act: 0.4890. Min Act: -0.1700
Data Index: 5691839 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19