Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5431 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.6713. Min Act: -0.1700
Data Index: 2118774 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.5775. Min Act: -0.1700
Data Index: 2118778 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.3900. Min Act: -0.1700
Data Index: 8785222 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.3275. Min Act: -0.1700
Data Index: 2118772 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.3275. Min Act: -0.1700
Data Index: 2198636 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.2963. Min Act: -0.1700
Data Index: 7258737 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.2963. Min Act: -0.1700
Data Index: 2118773 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.3275. Min Act: -0.1700
Data Index: 2118770 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.2650. Min Act: -0.1700
Data Index: 8417227 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.2338. Min Act: -0.1700
Data Index: 6835195 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.2338. Min Act: -0.1700
Data Index: 7790278 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.1713. Min Act: -0.1700
Data Index: 2538456 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.1713. Min Act: -0.1700
Data Index: 4833905 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.1400. Min Act: -0.1700
Data Index: 2333788 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.1400. Min Act: -0.1700
Data Index: 4624510 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.1088. Min Act: -0.1700
Data Index: 171283 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.1088. Min Act: -0.1700
Data Index: 2416146 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.0463. Min Act: -0.1700
Data Index: 2118771 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.0775. Min Act: -0.1700
Data Index: 1892515 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6713. Min Range: -5.6713
Max Act: 5.0775. Min Act: -0.1700
Data Index: 4743910 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19