Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6078 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.8110. Min Act: -0.1700
Data Index: 5755371 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.5610. Min Act: -0.1700
Data Index: 7141381 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.4672. Min Act: -0.1700
Data Index: 3157219 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.3735. Min Act: -0.1700
Data Index: 7190918 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.3735. Min Act: -0.1700
Data Index: 8385869 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.3422. Min Act: -0.1700
Data Index: 4876648 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.3110. Min Act: -0.1700
Data Index: 774923 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.2797. Min Act: -0.1700
Data Index: 3835916 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.2797. Min Act: -0.1700
Data Index: 4098369 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.2172. Min Act: -0.1700
Data Index: 7081983 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1547. Min Act: -0.1700
Data Index: 4030016 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1860. Min Act: -0.1700
Data Index: 7369725 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1860. Min Act: -0.1700
Data Index: 5287043 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1860. Min Act: -0.1700
Data Index: 5569008 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1860. Min Act: -0.1700
Data Index: 2059819 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1547. Min Act: -0.1700
Data Index: 7422181 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1547. Min Act: -0.1700
Data Index: 8227102 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1860. Min Act: -0.1700
Data Index: 4802393 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1547. Min Act: -0.1700
Data Index: 2713220 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8110. Min Range: -6.8110
Max Act: 6.1860. Min Act: -0.1700
Data Index: 6947190 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19