Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1735. Min Range: -5.1735
Max Act: 5.1735. Min Act: -0.1700
Data Index: 7154036 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1735. Min Range: -5.1735
Max Act: 5.0485. Min Act: -0.1700
Data Index: 4555994 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1735. Min Range: -5.1735
Max Act: 5.0173. Min Act: -0.1700
Data Index: 3217988 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1735. Min Range: -5.1735
Max Act: 5.0173. Min Act: -0.1700
Data Index: 4390800 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.9548. Min Act: -0.1700
Data Index: 5063152 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.8923. Min Act: -0.1700
Data Index: 4555995 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.8298. Min Act: -0.1700
Data Index: 8760156 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7673. Min Act: -0.1700
Data Index: 4763912 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7673. Min Act: -0.1700
Data Index: 1203541 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7360. Min Act: -0.1700
Data Index: 6472175 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7048. Min Act: -0.1700
Data Index: 6624539 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7048. Min Act: -0.1700
Data Index: 56697 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7048. Min Act: -0.1700
Data Index: 6846770 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7048. Min Act: -0.1700
Data Index: 1786474 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.7048. Min Act: -0.1700
Data Index: 4555993 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.6735. Min Act: -0.1700
Data Index: 1093296 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.6423. Min Act: -0.1700
Data Index: 2649182 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.6735. Min Act: -0.1700
Data Index: 7231280 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.6423. Min Act: -0.1700
Data Index: 6472176 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1735. Min Range: -5.1735
Max Act: 4.6423. Min Act: -0.1700
Data Index: 6472177 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19