Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2889 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1406. Min Range: -7.1406
Max Act: 7.1406. Min Act: -0.1700
Data Index: 1746324 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.9844. Min Act: -0.1700
Data Index: 5641293 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.7969. Min Act: -0.1700
Data Index: 6445141 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.7344. Min Act: -0.1700
Data Index: 995616 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.6719. Min Act: -0.1700
Data Index: 8489167 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.6094. Min Act: -0.1700
Data Index: 5491416 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.5781. Min Act: -0.1700
Data Index: 7829061 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.5469. Min Act: -0.1700
Data Index: 8731160 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.5469. Min Act: -0.1700
Data Index: 269535 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.5469. Min Act: -0.1700
Data Index: 2442109 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.5469. Min Act: -0.1700
Data Index: 4864877 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.4531. Min Act: -0.1700
Data Index: 8042579 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.4219. Min Act: -0.1700
Data Index: 8333434 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.4219. Min Act: -0.1700
Data Index: 7741836 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.4531. Min Act: -0.1700
Data Index: 5672034 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.4219. Min Act: -0.1700
Data Index: 898140 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.4219. Min Act: -0.1700
Data Index: 2975407 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.3906. Min Act: -0.1700
Data Index: 171770 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.3906. Min Act: -0.1700
Data Index: 5450708 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1406. Min Range: -7.1406
Max Act: 6.3906. Min Act: -0.1700
Data Index: 5693784 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19