Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4368 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9923. Min Act: -0.1700
Data Index: 8034153 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9610. Min Act: -0.1700
Data Index: 2993228 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 3000008 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 8332207 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8985. Min Act: -0.1700
Data Index: 5691525 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 127588 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8360. Min Act: -0.1700
Data Index: 2648582 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 25677 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8360. Min Act: -0.1700
Data Index: 4119517 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 111241 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7392986 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8048. Min Act: -0.1700
Data Index: 8182838 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 5798855 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 746248 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 2681762 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 7144789 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 4686668 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 7198036 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 3381391 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.6798. Min Act: -0.1700
Data Index: 3130990 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19