Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2743. Min Range: -7.2743
Max Act: 7.2430. Min Act: -0.1700
Data Index: 95355 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2743. Min Range: -7.2743
Max Act: 7.2743. Min Act: -0.1700
Data Index: 8700351 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2743. Min Range: -7.2743
Max Act: 7.1805. Min Act: -0.1700
Data Index: 8327314 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2743. Min Range: -7.2743
Max Act: 7.0868. Min Act: -0.1700
Data Index: 7552448 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.9305. Min Act: -0.1700
Data Index: 3612918 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.8680. Min Act: -0.1700
Data Index: 5240955 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.8368. Min Act: -0.1700
Data Index: 8242676 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7743. Min Act: -0.1700
Data Index: 2311752 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7743. Min Act: -0.1700
Data Index: 8242681 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.8368. Min Act: -0.1700
Data Index: 3982387 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.8055. Min Act: -0.1700
Data Index: 6234047 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7743. Min Act: -0.1700
Data Index: 5957472 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7743. Min Act: -0.1700
Data Index: 8806881 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7430. Min Act: -0.1700
Data Index: 2765612 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7118. Min Act: -0.1700
Data Index: 4342739 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7118. Min Act: -0.1700
Data Index: 5828983 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.7118. Min Act: -0.1700
Data Index: 6543034 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.6805. Min Act: -0.1700
Data Index: 3235912 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.6493. Min Act: -0.1700
Data Index: 121284 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2743. Min Range: -7.2743
Max Act: 6.6180. Min Act: -0.1700
Data Index: 7624743 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19