Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3409. Min Range: -6.3409
Max Act: 6.3409. Min Act: -0.1700
Data Index: 6711955 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3409. Min Range: -6.3409
Max Act: 6.1847. Min Act: -0.1700
Data Index: 434640 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.9972. Min Act: -0.1700
Data Index: 196608 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3409. Min Range: -6.3409
Max Act: 6.0284. Min Act: -0.1700
Data Index: 5052032 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.9347. Min Act: -0.1700
Data Index: 4513573 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.9034. Min Act: -0.1700
Data Index: 4094480 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8722. Min Act: -0.1700
Data Index: 4932421 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.9034. Min Act: -0.1700
Data Index: 3459483 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8722. Min Act: -0.1700
Data Index: 2708101 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8409. Min Act: -0.1700
Data Index: 6569133 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8409. Min Act: -0.1700
Data Index: 1511965 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8722. Min Act: -0.1700
Data Index: 7010960 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8409. Min Act: -0.1700
Data Index: 5137183 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8097. Min Act: -0.1700
Data Index: 1488723 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.8409. Min Act: -0.1700
Data Index: 1551509 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.7784. Min Act: -0.1700
Data Index: 8626678 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.7784. Min Act: -0.1700
Data Index: 3053942 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.7472. Min Act: -0.1700
Data Index: 7216568 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.7159. Min Act: -0.1700
Data Index: 622912 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3409. Min Range: -6.3409
Max Act: 5.7159. Min Act: -0.1700
Data Index: 1667732 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19