Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5962 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0655. Min Range: -7.0655
Max Act: 7.0655. Min Act: -0.1700
Data Index: 90279 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0655. Min Range: -7.0655
Max Act: 7.0030. Min Act: -0.1700
Data Index: 4464046 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0655. Min Range: -7.0655
Max Act: 7.0030. Min Act: -0.1700
Data Index: 5775830 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0655. Min Range: -7.0655
Max Act: 7.0030. Min Act: -0.1700
Data Index: 2867892 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.9717. Min Act: -0.1700
Data Index: 3922049 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.8780. Min Act: -0.1700
Data Index: 4679001 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.8467. Min Act: -0.1700
Data Index: 4220540 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.8467. Min Act: -0.1700
Data Index: 1514483 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.8155. Min Act: -0.1700
Data Index: 2544153 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7842. Min Act: -0.1700
Data Index: 5904789 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7842. Min Act: -0.1700
Data Index: 3952385 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7530. Min Act: -0.1700
Data Index: 7411869 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7530. Min Act: -0.1700
Data Index: 1012723 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7530. Min Act: -0.1700
Data Index: 4982604 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7530. Min Act: -0.1700
Data Index: 3105428 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7530. Min Act: -0.1700
Data Index: 212192 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.7217. Min Act: -0.1700
Data Index: 3922976 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.6905. Min Act: -0.1700
Data Index: 8571581 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.6592. Min Act: -0.1700
Data Index: 5347574 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0655. Min Range: -7.0655
Max Act: 6.6905. Min Act: -0.1700
Data Index: 2935690 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19