Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1307 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.7863. Min Act: -0.1700
Data Index: 2091948 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.5988. Min Act: -0.1700
Data Index: 6883574 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.5676. Min Act: -0.1700
Data Index: 1182023 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.5676. Min Act: -0.1700
Data Index: 797827 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.5363. Min Act: -0.1700
Data Index: 6275738 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.5051. Min Act: -0.1700
Data Index: 111019 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.4426. Min Act: -0.1700
Data Index: 7955519 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.4113. Min Act: -0.1700
Data Index: 4632830 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.4113. Min Act: -0.1700
Data Index: 2711161 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.4113. Min Act: -0.1700
Data Index: 8292554 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2825454 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.4113. Min Act: -0.1700
Data Index: 4020722 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3801. Min Act: -0.1700
Data Index: 1740016 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.4113. Min Act: -0.1700
Data Index: 2448114 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3801. Min Act: -0.1700
Data Index: 2769964 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3801. Min Act: -0.1700
Data Index: 7318623 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3488. Min Act: -0.1700
Data Index: 568507 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3488. Min Act: -0.1700
Data Index: 523559 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3488. Min Act: -0.1700
Data Index: 4023524 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7863. Min Range: -5.7863
Max Act: 5.3176. Min Act: -0.1700
Data Index: 6932347 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19