Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.4861. Min Act: -0.1700
Data Index: 569943 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3924. Min Act: -0.1700
Data Index: 5137169 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3924. Min Act: -0.1700
Data Index: 8657234 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3924. Min Act: -0.1700
Data Index: 4416117 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3924. Min Act: -0.1700
Data Index: 1236043 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3611. Min Act: -0.1700
Data Index: 8349212 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3611. Min Act: -0.1700
Data Index: 6489433 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3298. Min Act: -0.1700
Data Index: 5950651 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2986. Min Act: -0.1700
Data Index: 8611407 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.3298. Min Act: -0.1700
Data Index: 1138602 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2673. Min Act: -0.1700
Data Index: 4445919 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2673. Min Act: -0.1700
Data Index: 1030791 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2673. Min Act: -0.1700
Data Index: 7337603 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2673. Min Act: -0.1700
Data Index: 4730321 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2361. Min Act: -0.1700
Data Index: 6284676 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2361. Min Act: -0.1700
Data Index: 891058 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2048. Min Act: -0.1700
Data Index: 6728979 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2048. Min Act: -0.1700
Data Index: 6926588 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2361. Min Act: -0.1700
Data Index: 6017897 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4861. Min Range: -4.4861
Max Act: 4.2048. Min Act: -0.1700
Data Index: 1671009 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19