Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2653 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2548. Min Range: -8.2548
Max Act: 8.2548. Min Act: -0.1700
Data Index: 197253 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2548. Min Range: -8.2548
Max Act: 8.0673. Min Act: -0.1700
Data Index: 6672326 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.9423. Min Act: -0.1700
Data Index: 2681511 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.8485. Min Act: -0.1700
Data Index: 1607104 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.8798. Min Act: -0.1700
Data Index: 339998 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.8173. Min Act: -0.1700
Data Index: 7234720 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.7548. Min Act: -0.1700
Data Index: 7256983 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.7860. Min Act: -0.1700
Data Index: 1537059 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.6923. Min Act: -0.1700
Data Index: 3791343 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.6298. Min Act: -0.1700
Data Index: 1553877 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.6298. Min Act: -0.1700
Data Index: 86662 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.6298. Min Act: -0.1700
Data Index: 2121705 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.5673. Min Act: -0.1700
Data Index: 3474795 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.5360. Min Act: -0.1700
Data Index: 628008 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.5360. Min Act: -0.1700
Data Index: 7857325 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.4735. Min Act: -0.1700
Data Index: 2457794 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.4110. Min Act: -0.1700
Data Index: 3292372 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.4110. Min Act: -0.1700
Data Index: 5791853 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.4110. Min Act: -0.1700
Data Index: 4330718 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2548. Min Range: -8.2548
Max Act: 7.4110. Min Act: -0.1700
Data Index: 3766399 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19