Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.9025. Min Act: -0.1700
Data Index: 544725 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.8088. Min Act: -0.1700
Data Index: 2541401 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.7463. Min Act: -0.1700
Data Index: 2603293 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.6525. Min Act: -0.1700
Data Index: 4742347 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.6838. Min Act: -0.1700
Data Index: 1221312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.6525. Min Act: -0.1700
Data Index: 7519032 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.5900. Min Act: -0.1700
Data Index: 2754323 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.5588. Min Act: -0.1700
Data Index: 3921717 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.5588. Min Act: -0.1700
Data Index: 2396771 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.5588. Min Act: -0.1700
Data Index: 3812651 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.4963. Min Act: -0.1700
Data Index: 4745490 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.4963. Min Act: -0.1700
Data Index: 4488907 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.4650. Min Act: -0.1700
Data Index: 435355 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.4338. Min Act: -0.1700
Data Index: 3063027 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.4025. Min Act: -0.1700
Data Index: 1589801 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.4025. Min Act: -0.1700
Data Index: 4909613 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.3400. Min Act: -0.1700
Data Index: 2558893 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.3088. Min Act: -0.1700
Data Index: 6149954 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.3400. Min Act: -0.1700
Data Index: 1998874 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9025. Min Range: -6.9025
Max Act: 6.3400. Min Act: -0.1700
Data Index: 296467 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19