Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.9248. Min Act: -0.1700
Data Index: 8023739 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.8931. Min Act: -0.1700
Data Index: 4083190 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.8772. Min Act: -0.1700
Data Index: 8712734 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.7818. Min Act: -0.1700
Data Index: 7062987 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.7499. Min Act: -0.1700
Data Index: 3437896 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.7499. Min Act: -0.1700
Data Index: 7258364 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.7499. Min Act: -0.1700
Data Index: 1537732 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.7179. Min Act: -0.1700
Data Index: 4685415 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.7020. Min Act: -0.1700
Data Index: 3729490 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.7020. Min Act: -0.1700
Data Index: 2050018 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6859. Min Act: -0.1700
Data Index: 4639380 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6699. Min Act: -0.1700
Data Index: 1899568 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6859. Min Act: -0.1700
Data Index: 874074 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6699. Min Act: -0.1700
Data Index: 5357161 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6859. Min Act: -0.1700
Data Index: 1763239 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6699. Min Act: -0.1700
Data Index: 3879789 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6378. Min Act: -0.1700
Data Index: 4639384 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6539. Min Act: -0.1700
Data Index: 3341118 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6699. Min Act: -0.1700
Data Index: 7951348 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9248. Min Range: -2.9248
Max Act: 2.6378. Min Act: -0.1700
Data Index: 3288289 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19