Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.5048. Min Act: -0.1700
Data Index: 170840 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.3798. Min Act: -0.1700
Data Index: 3611735 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.3485. Min Act: -0.1700
Data Index: 2641748 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.2235. Min Act: -0.1700
Data Index: 5428616 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.2548. Min Act: -0.1700
Data Index: 4234873 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.2235. Min Act: -0.1700
Data Index: 2782244 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.2235. Min Act: -0.1700
Data Index: 1366702 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.1610. Min Act: -0.1700
Data Index: 5506831 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.1923. Min Act: -0.1700
Data Index: 6511434 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.1298. Min Act: -0.1700
Data Index: 36351 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.1298. Min Act: -0.1700
Data Index: 1368706 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.1298. Min Act: -0.1700
Data Index: 3140382 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.0985. Min Act: -0.1700
Data Index: 2298427 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.1298. Min Act: -0.1700
Data Index: 2644581 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.0672. Min Act: -0.1700
Data Index: 4883219 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.0672. Min Act: -0.1700
Data Index: 8670326 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.0672. Min Act: -0.1700
Data Index: 3298673 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.0672. Min Act: -0.1700
Data Index: 8211960 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.0672. Min Act: -0.1700
Data Index: 7927271 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5048. Min Range: -4.5048
Max Act: 4.0360. Min Act: -0.1700
Data Index: 5763997 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19