Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 248 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.9418. Min Act: -0.1700
Data Index: 4851462 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.6293. Min Act: -0.1700
Data Index: 3354633 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.5980. Min Act: -0.1700
Data Index: 7056347 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.5668. Min Act: -0.1700
Data Index: 2165700 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.5355. Min Act: -0.1700
Data Index: 960771 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.5355. Min Act: -0.1700
Data Index: 1913934 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.5355. Min Act: -0.1700
Data Index: 1989027 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.5668. Min Act: -0.1700
Data Index: 7065308 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.5355. Min Act: -0.1700
Data Index: 7777909 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4105. Min Act: -0.1700
Data Index: 791083 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4730. Min Act: -0.1700
Data Index: 2785224 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4418. Min Act: -0.1700
Data Index: 1165049 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4105. Min Act: -0.1700
Data Index: 5125966 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4105. Min Act: -0.1700
Data Index: 103421 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4105. Min Act: -0.1700
Data Index: 4804855 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4105. Min Act: -0.1700
Data Index: 8143354 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4105. Min Act: -0.1700
Data Index: 7166548 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.4105. Min Act: -0.1700
Data Index: 7873800 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.3793. Min Act: -0.1700
Data Index: 1205151 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9418. Min Range: -4.9418
Max Act: 4.3793. Min Act: -0.1700
Data Index: 6826562 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19