Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1544. Min Range: -8.1544
Max Act: 8.1544. Min Act: -0.1700
Data Index: 2299106 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1544. Min Range: -8.1544
Max Act: 8.1231. Min Act: -0.1700
Data Index: 5701583 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.9044. Min Act: -0.1700
Data Index: 6421670 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.8419. Min Act: -0.1700
Data Index: 7173177 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.7794. Min Act: -0.1700
Data Index: 6685704 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.7169. Min Act: -0.1700
Data Index: 2831826 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.6856. Min Act: -0.1700
Data Index: 508801 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.6231. Min Act: -0.1700
Data Index: 3818036 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.6231. Min Act: -0.1700
Data Index: 5761773 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.5294. Min Act: -0.1700
Data Index: 3818032 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.5606. Min Act: -0.1700
Data Index: 2182601 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.4669. Min Act: -0.1700
Data Index: 3451623 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.4356. Min Act: -0.1700
Data Index: 4189675 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.4356. Min Act: -0.1700
Data Index: 6178548 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.3731. Min Act: -0.1700
Data Index: 687063 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.3731. Min Act: -0.1700
Data Index: 7173174 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.3731. Min Act: -0.1700
Data Index: 5865866 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.3731. Min Act: -0.1700
Data Index: 2429463 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.2794. Min Act: -0.1700
Data Index: 390792 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1544. Min Range: -8.1544
Max Act: 7.3106. Min Act: -0.1700
Data Index: 334938 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19