Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5318 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.7700. Min Act: -0.1700
Data Index: 5800565 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.6450. Min Act: -0.1700
Data Index: 8674366 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.5825. Min Act: -0.1700
Data Index: 5684085 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.5513. Min Act: -0.1700
Data Index: 8365169 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.5513. Min Act: -0.1700
Data Index: 5608757 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.4575. Min Act: -0.1700
Data Index: 7660754 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.4263. Min Act: -0.1700
Data Index: 7504641 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.4263. Min Act: -0.1700
Data Index: 7819905 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3638. Min Act: -0.1700
Data Index: 8785815 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3638. Min Act: -0.1700
Data Index: 930301 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3638. Min Act: -0.1700
Data Index: 4127509 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3325. Min Act: -0.1700
Data Index: 6681124 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3325. Min Act: -0.1700
Data Index: 2351003 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3325. Min Act: -0.1700
Data Index: 3603843 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3325. Min Act: -0.1700
Data Index: 4713457 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3013. Min Act: -0.1700
Data Index: 524909 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.3013. Min Act: -0.1700
Data Index: 3320673 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.2700. Min Act: -0.1700
Data Index: 1058771 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.2700. Min Act: -0.1700
Data Index: 48776 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7700. Min Range: -5.7700
Max Act: 5.2700. Min Act: -0.1700
Data Index: 1521858 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19