Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.5614. Min Act: -0.1700
Data Index: 2700300 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.4364. Min Act: -0.1700
Data Index: 6991704 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.3739. Min Act: -0.1700
Data Index: 8379387 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2176. Min Act: -0.1700
Data Index: 2332095 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.1864. Min Act: -0.1700
Data Index: 748275 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0926. Min Act: -0.1700
Data Index: 3319617 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0926. Min Act: -0.1700
Data Index: 644542 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 2103934 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 7338305 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 4952959 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 8303626 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0301. Min Act: -0.1700
Data Index: 2617234 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 1653273 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 4755829 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 4665903 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9676. Min Act: -0.1700
Data Index: 717131 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 1504869 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 8762573 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9364. Min Act: -0.1700
Data Index: 5541231 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9676. Min Act: -0.1700
Data Index: 5756779 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19