Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5076 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.4842. Min Act: -0.1700
Data Index: 8480579 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.4529. Min Act: -0.1700
Data Index: 760875 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.4217. Min Act: -0.1700
Data Index: 6585955 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.3279. Min Act: -0.1700
Data Index: 5372078 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.3279. Min Act: -0.1700
Data Index: 5324033 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2967. Min Act: -0.1700
Data Index: 4459693 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2967. Min Act: -0.1700
Data Index: 2039249 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2967. Min Act: -0.1700
Data Index: 3997969 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2654. Min Act: -0.1700
Data Index: 5574549 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2654. Min Act: -0.1700
Data Index: 4828234 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2654. Min Act: -0.1700
Data Index: 8447465 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2654. Min Act: -0.1700
Data Index: 2347210 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2654. Min Act: -0.1700
Data Index: 8483459 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2029. Min Act: -0.1700
Data Index: 1113310 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2654. Min Act: -0.1700
Data Index: 2742659 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2342. Min Act: -0.1700
Data Index: 5969165 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2342. Min Act: -0.1700
Data Index: 4116270 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2029. Min Act: -0.1700
Data Index: 7462891 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2029. Min Act: -0.1700
Data Index: 8045410 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4842. Min Range: -6.4842
Max Act: 6.2029. Min Act: -0.1700
Data Index: 8218652 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19