Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5006 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1892. Min Range: -10.1892
Max Act: 10.1892. Min Act: -0.1700
Data Index: 1591577 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1892. Min Range: -10.1892
Max Act: 10.1267. Min Act: -0.1700
Data Index: 2080417 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1892. Min Range: -10.1892
Max Act: 10.0642. Min Act: -0.1700
Data Index: 5327397 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1892. Min Range: -10.1892
Max Act: 10.0017. Min Act: -0.1700
Data Index: 3117368 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.9392. Min Act: -0.1700
Data Index: 6323413 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.8767. Min Act: -0.1700
Data Index: 7424944 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.9392. Min Act: -0.1700
Data Index: 1009174 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.8767. Min Act: -0.1700
Data Index: 6343752 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.8142. Min Act: -0.1700
Data Index: 7664056 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.8142. Min Act: -0.1700
Data Index: 3554138 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.8142. Min Act: -0.1700
Data Index: 2842950 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.7517. Min Act: -0.1700
Data Index: 6806306 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.7517. Min Act: -0.1700
Data Index: 6417140 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.6892. Min Act: -0.1700
Data Index: 7956916 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.6892. Min Act: -0.1700
Data Index: 887011 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.6892. Min Act: -0.1700
Data Index: 4390147 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.6892. Min Act: -0.1700
Data Index: 7935290 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.6267. Min Act: -0.1700
Data Index: 6424878 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.6267. Min Act: -0.1700
Data Index: 1020837 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1892. Min Range: -10.1892
Max Act: 9.6267. Min Act: -0.1700
Data Index: 7583478 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19