Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5113. Min Range: -6.5113
Max Act: 6.5113. Min Act: -0.1700
Data Index: 625078 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5113. Min Range: -6.5113
Max Act: 6.4175. Min Act: -0.1700
Data Index: 4143218 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5113. Min Range: -6.5113
Max Act: 6.1363. Min Act: -0.1700
Data Index: 5817998 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5113. Min Range: -6.5113
Max Act: 6.0738. Min Act: -0.1700
Data Index: 3981633 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.9800. Min Act: -0.1700
Data Index: 8662669 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.9800. Min Act: -0.1700
Data Index: 8576093 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.9488. Min Act: -0.1700
Data Index: 5045241 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.8550. Min Act: -0.1700
Data Index: 547654 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.7613. Min Act: -0.1700
Data Index: 7856419 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.7300. Min Act: -0.1700
Data Index: 5490009 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.7300. Min Act: -0.1700
Data Index: 933920 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6988. Min Act: -0.1700
Data Index: 2107212 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6675. Min Act: -0.1700
Data Index: 145247 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6675. Min Act: -0.1700
Data Index: 2198366 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6675. Min Act: -0.1700
Data Index: 2987349 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6050. Min Act: -0.1700
Data Index: 2532700 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6363. Min Act: -0.1700
Data Index: 1028858 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6363. Min Act: -0.1700
Data Index: 8007589 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6050. Min Act: -0.1700
Data Index: 5351642 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5113. Min Range: -6.5113
Max Act: 5.6050. Min Act: -0.1700
Data Index: 4098655 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19