Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0456. Min Range: -7.0456
Max Act: 7.0456. Min Act: -0.1700
Data Index: 792268 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.8894. Min Act: -0.1700
Data Index: 6184998 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.8581. Min Act: -0.1700
Data Index: 3909774 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7331. Min Act: -0.1700
Data Index: 1317556 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.7019. Min Act: -0.1698
Data Index: 1164613 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.6081. Min Act: -0.1700
Data Index: 4314920 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.5456. Min Act: -0.1700
Data Index: 3342413 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.5456. Min Act: -0.1700
Data Index: 7653488 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.5456. Min Act: -0.1700
Data Index: 6191430 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.5456. Min Act: -0.1700
Data Index: 3265268 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4831. Min Act: -0.1700
Data Index: 3615692 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.5144. Min Act: -0.1700
Data Index: 4356975 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.5144. Min Act: -0.1700
Data Index: 8494908 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4831. Min Act: -0.1700
Data Index: 2394565 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4519. Min Act: -0.1700
Data Index: 652549 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4206. Min Act: -0.1700
Data Index: 1815879 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4206. Min Act: -0.1700
Data Index: 5458633 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4206. Min Act: -0.1699
Data Index: 1793974 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4206. Min Act: -0.1700
Data Index: 4659134 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0456. Min Range: -7.0456
Max Act: 6.4206. Min Act: -0.1700
Data Index: 3910924 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19