Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.3234. Min Range: -16.3234
Max Act: 16.3234. Min Act: -0.1700
Data Index: 1565379 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.3234. Min Range: -16.3234
Max Act: 16.3234. Min Act: -0.1700
Data Index: 2829808 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.3234. Min Range: -16.3234
Max Act: 16.1984. Min Act: -0.1700
Data Index: 5136712 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.9484. Min Act: -0.1700
Data Index: 3745674 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.3234. Min Range: -16.3234
Max Act: 16.0734. Min Act: -0.1700
Data Index: 1798935 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.3234. Min Range: -16.3234
Max Act: 16.0734. Min Act: -0.1700
Data Index: 2379994 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.9484. Min Act: -0.1700
Data Index: 1292843 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.9484. Min Act: -0.1700
Data Index: 8762618 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.8859. Min Act: -0.1700
Data Index: 7247935 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.8234. Min Act: -0.1700
Data Index: 7011049 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.8859. Min Act: -0.1700
Data Index: 6492407 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.8234. Min Act: -0.1700
Data Index: 3627889 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.8234. Min Act: -0.1700
Data Index: 4057491 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.8234. Min Act: -0.1700
Data Index: 2580011 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.8234. Min Act: -0.1700
Data Index: 1198362 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.7609. Min Act: -0.1700
Data Index: 6047850 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.7609. Min Act: -0.1700
Data Index: 4083453 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.7609. Min Act: -0.1700
Data Index: 6002216 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.7609. Min Act: -0.1700
Data Index: 492118 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.3234. Min Range: -16.3234
Max Act: 15.7609. Min Act: -0.1700
Data Index: 5248406 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19