Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.4416. Min Act: -0.1700
Data Index: 3400071 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.2228. Min Act: -0.1700
Data Index: 2921772 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.2541. Min Act: -0.1700
Data Index: 4447368 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.2541. Min Act: -0.1700
Data Index: 1839523 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.2228. Min Act: -0.1700
Data Index: 7056645 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.2228. Min Act: -0.1700
Data Index: 7857655 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.1603. Min Act: -0.1700
Data Index: 7688538 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.1603. Min Act: -0.1700
Data Index: 8255600 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0978. Min Act: -0.1700
Data Index: 3095795 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0978. Min Act: -0.1700
Data Index: 492270 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0978. Min Act: -0.1700
Data Index: 6739605 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.1291. Min Act: -0.1700
Data Index: 5250370 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0666. Min Act: -0.1700
Data Index: 8062060 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0041. Min Act: -0.1700
Data Index: 5879695 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0353. Min Act: -0.1700
Data Index: 4115616 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0353. Min Act: -0.1700
Data Index: 7256947 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0041. Min Act: -0.1700
Data Index: 6591531 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0041. Min Act: -0.1700
Data Index: 6182012 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4416. Min Range: -5.4416
Max Act: 5.0041. Min Act: -0.1700
Data Index: 1990319 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4416. Min Range: -5.4416
Max Act: 4.9416. Min Act: -0.1700
Data Index: 5012170 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19