Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 876 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.5610. Min Act: -0.1700
Data Index: 2605411 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.3422. Min Act: -0.1700
Data Index: 4719533 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.3422. Min Act: -0.1700
Data Index: 8757835 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.2797. Min Act: -0.1700
Data Index: 7961509 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.2797. Min Act: -0.1700
Data Index: 106953 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.1860. Min Act: -0.1700
Data Index: 2076957 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.1547. Min Act: -0.1700
Data Index: 7388587 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.1547. Min Act: -0.1700
Data Index: 1168768 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.0610. Min Act: -0.1700
Data Index: 7410918 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5610. Min Range: -7.5610
Max Act: 7.0297. Min Act: -0.1700
Data Index: 1958556 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.9985. Min Act: -0.1700
Data Index: 1347758 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.9360. Min Act: -0.1700
Data Index: 4216877 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.9047. Min Act: -0.1700
Data Index: 3598816 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.8735. Min Act: -0.1700
Data Index: 2076954 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.9047. Min Act: -0.1700
Data Index: 7752544 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.9047. Min Act: -0.1700
Data Index: 7829247 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.9047. Min Act: -0.1700
Data Index: 1730997 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.9047. Min Act: -0.1700
Data Index: 2782515 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.8422. Min Act: -0.1700
Data Index: 2368139 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5610. Min Range: -7.5610
Max Act: 6.8735. Min Act: -0.1700
Data Index: 5314160 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19