Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4977 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2058. Min Range: -5.2058
Max Act: 5.2058. Min Act: -0.1700
Data Index: 7759410 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2058. Min Range: -5.2058
Max Act: 5.1433. Min Act: -0.1700
Data Index: 6668278 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2058. Min Range: -5.2058
Max Act: 5.1120. Min Act: -0.1700
Data Index: 7759409 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2058. Min Range: -5.2058
Max Act: 5.0183. Min Act: -0.1700
Data Index: 7759412 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2058. Min Range: -5.2058
Max Act: 5.0183. Min Act: -0.1700
Data Index: 2156034 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2058. Min Range: -5.2058
Max Act: 5.0183. Min Act: -0.1700
Data Index: 338211 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8933. Min Act: -0.1700
Data Index: 5034321 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.9245. Min Act: -0.1700
Data Index: 8810041 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8933. Min Act: -0.1700
Data Index: 4109755 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8933. Min Act: -0.1700
Data Index: 6338949 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8933. Min Act: -0.1700
Data Index: 2536221 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8933. Min Act: -0.1700
Data Index: 4922928 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8933. Min Act: -0.1700
Data Index: 3218691 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8620. Min Act: -0.1700
Data Index: 7865124 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8620. Min Act: -0.1700
Data Index: 8667440 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8620. Min Act: -0.1700
Data Index: 6448645 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8620. Min Act: -0.1700
Data Index: 7759408 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8620. Min Act: -0.1700
Data Index: 928956 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8620. Min Act: -0.1700
Data Index: 6492832 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2058. Min Range: -5.2058
Max Act: 4.8308. Min Act: -0.1700
Data Index: 4690453 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19