Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5418 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.6450. Min Act: -0.1700
Data Index: 497690 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4575. Min Act: -0.1700
Data Index: 1781857 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4575. Min Act: -0.1700
Data Index: 1781856 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4575. Min Act: -0.1700
Data Index: 6846235 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.4263. Min Act: -0.1700
Data Index: 5021698 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3950. Min Act: -0.1700
Data Index: 8599824 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3950. Min Act: -0.1700
Data Index: 5406155 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3950. Min Act: -0.1700
Data Index: 3032555 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3950. Min Act: -0.1700
Data Index: 6060078 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3638. Min Act: -0.1700
Data Index: 2663815 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3638. Min Act: -0.1700
Data Index: 7625206 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 6249691 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 1703096 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 7662707 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 7869869 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 4705668 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 4814552 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3325. Min Act: -0.1700
Data Index: 506630 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3013. Min Act: -0.1700
Data Index: 1781854 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6450. Min Range: -5.6450
Max Act: 5.3013. Min Act: -0.1700
Data Index: 3601065 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19