Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3686 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2015. Min Range: -5.2015
Max Act: 5.2015. Min Act: -0.1700
Data Index: 5912456 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.8890. Min Act: -0.1700
Data Index: 7612963 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.7328. Min Act: -0.1700
Data Index: 7956921 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.7328. Min Act: -0.1700
Data Index: 5625970 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.7328. Min Act: -0.1700
Data Index: 4383656 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.7328. Min Act: -0.1700
Data Index: 4329031 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.6390. Min Act: -0.1700
Data Index: 1435455 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.6390. Min Act: -0.1700
Data Index: 7301798 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.6390. Min Act: -0.1700
Data Index: 6927804 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.6078. Min Act: -0.1700
Data Index: 4877270 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5765. Min Act: -0.1700
Data Index: 5596513 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5765. Min Act: -0.1700
Data Index: 7194953 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5765. Min Act: -0.1700
Data Index: 4281939 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5765. Min Act: -0.1700
Data Index: 6343402 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5453. Min Act: -0.1700
Data Index: 807852 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5765. Min Act: -0.1700
Data Index: 403455 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5765. Min Act: -0.1700
Data Index: 6194233 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5765. Min Act: -0.1700
Data Index: 369044 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5453. Min Act: -0.1700
Data Index: 7301799 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2015. Min Range: -5.2015
Max Act: 4.5453. Min Act: -0.1700
Data Index: 4316042 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19