Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2793 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3611. Min Range: -5.3611
Max Act: 5.3611. Min Act: -0.1700
Data Index: 4406495 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3611. Min Range: -5.3611
Max Act: 5.2361. Min Act: -0.1700
Data Index: 1761759 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3611. Min Range: -5.3611
Max Act: 5.2048. Min Act: -0.1700
Data Index: 2928943 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3611. Min Range: -5.3611
Max Act: 5.1736. Min Act: -0.1700
Data Index: 4481262 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3611. Min Range: -5.3611
Max Act: 5.0798. Min Act: -0.1700
Data Index: 1192057 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9861. Min Act: -0.1700
Data Index: 3868772 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9861. Min Act: -0.1700
Data Index: 8451373 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9861. Min Act: -0.1700
Data Index: 7920402 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9548. Min Act: -0.1700
Data Index: 6196163 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9236. Min Act: -0.1700
Data Index: 4374902 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9236. Min Act: -0.1700
Data Index: 6196168 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9236. Min Act: -0.1700
Data Index: 6187523 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.9236. Min Act: -0.1700
Data Index: 6480471 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.8923. Min Act: -0.1700
Data Index: 6311788 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.8923. Min Act: -0.1700
Data Index: 4506084 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.8611. Min Act: -0.1700
Data Index: 4279887 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.8611. Min Act: -0.1700
Data Index: 4188432 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.8611. Min Act: -0.1700
Data Index: 2241277 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.8611. Min Act: -0.1700
Data Index: 3868739 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3611. Min Range: -5.3611
Max Act: 4.8298. Min Act: -0.1700
Data Index: 2083228 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19