Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.5532. Min Act: -0.1700
Data Index: 8604514 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.4594. Min Act: -0.1700
Data Index: 8604513 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.2719. Min Act: -0.1700
Data Index: 2355192 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.2407. Min Act: -0.1700
Data Index: 8604512 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.2407. Min Act: -0.1700
Data Index: 6629770 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.1782. Min Act: -0.1700
Data Index: 3436329 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0531. Min Act: -0.1700
Data Index: 7716302 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 7904740 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0531. Min Act: -0.1700
Data Index: 6525074 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 8604515 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 6621350 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 3781613 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 7552971 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 7900177 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 3446864 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5532. Min Range: -4.5532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 6514071 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5532. Min Range: -4.5532
Max Act: 3.9906. Min Act: -0.1700
Data Index: 2716810 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5532. Min Range: -4.5532
Max Act: 3.9906. Min Act: -0.1700
Data Index: 7318043 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5532. Min Range: -4.5532
Max Act: 3.9906. Min Act: -0.1700
Data Index: 4313809 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5532. Min Range: -4.5532
Max Act: 3.9594. Min Act: -0.1700
Data Index: 1582073 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19