Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5521. Min Range: -10.5521
Max Act: 10.4896. Min Act: -0.1700
Data Index: 1496151 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5521. Min Range: -10.5521
Max Act: 10.5521. Min Act: -0.1700
Data Index: 1606201 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5521. Min Range: -10.5521
Max Act: 10.1771. Min Act: -0.1700
Data Index: 7883872 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5521. Min Range: -10.5521
Max Act: 10.1146. Min Act: -0.1700
Data Index: 1567399 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5521. Min Range: -10.5521
Max Act: 10.1146. Min Act: -0.1700
Data Index: 8077589 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5521. Min Range: -10.5521
Max Act: 10.0521. Min Act: -0.1700
Data Index: 7724671 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5521. Min Range: -10.5521
Max Act: 10.0521. Min Act: -0.1700
Data Index: 1295034 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.9896. Min Act: -0.1700
Data Index: 5082330 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.9896. Min Act: -0.1700
Data Index: 741076 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.9896. Min Act: -0.1700
Data Index: 1625011 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.9271. Min Act: -0.1700
Data Index: 3638995 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.9896. Min Act: -0.1700
Data Index: 7619409 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.9271. Min Act: -0.1700
Data Index: 1379067 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.8646. Min Act: -0.1700
Data Index: 3655470 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.8646. Min Act: -0.1700
Data Index: 5141898 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.8646. Min Act: -0.1700
Data Index: 5302274 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.8021. Min Act: -0.1700
Data Index: 1732107 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.8021. Min Act: -0.1700
Data Index: 591265 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.8021. Min Act: -0.1700
Data Index: 4135584 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5521. Min Range: -10.5521
Max Act: 9.8021. Min Act: -0.1700
Data Index: 2552199 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19