Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.1447. Min Act: -0.1700
Data Index: 2925623 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.1135. Min Act: -0.1700
Data Index: 2925646 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.1135. Min Act: -0.1700
Data Index: 2925626 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.1135. Min Act: -0.1700
Data Index: 3817478 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.0510. Min Act: -0.1700
Data Index: 4385883 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.0510. Min Act: -0.1700
Data Index: 6799337 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.0197. Min Act: -0.1700
Data Index: 5259016 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.0197. Min Act: -0.1700
Data Index: 4969379 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1447. Min Range: -5.1447
Max Act: 5.0510. Min Act: -0.1700
Data Index: 4492279 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9885. Min Act: -0.1700
Data Index: 4705598 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9572. Min Act: -0.1700
Data Index: 4969374 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9572. Min Act: -0.1700
Data Index: 2886139 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9572. Min Act: -0.1700
Data Index: 6799339 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9572. Min Act: -0.1700
Data Index: 7388475 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.8947. Min Act: -0.1700
Data Index: 4709065 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9260. Min Act: -0.1700
Data Index: 2925653 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9260. Min Act: -0.1700
Data Index: 4705599 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.8947. Min Act: -0.1700
Data Index: 596594 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9260. Min Act: -0.1700
Data Index: 4550629 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1447. Min Range: -5.1447
Max Act: 4.9260. Min Act: -0.1700
Data Index: 3326032 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19