Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1999 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3199. Min Range: -4.3199
Max Act: 4.3199. Min Act: -0.1700
Data Index: 1242451 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3199. Min Range: -4.3199
Max Act: 4.0386. Min Act: -0.1700
Data Index: 8446159 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3199. Min Range: -4.3199
Max Act: 4.0386. Min Act: -0.1700
Data Index: 6115155 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3199. Min Range: -4.3199
Max Act: 4.0386. Min Act: -0.1700
Data Index: 4672325 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3199. Min Range: -4.3199
Max Act: 4.0073. Min Act: -0.1700
Data Index: 1432979 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.9760. Min Act: -0.1700
Data Index: 5856718 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.9448. Min Act: -0.1700
Data Index: 8813399 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.9448. Min Act: -0.1700
Data Index: 6494854 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.9135. Min Act: -0.1700
Data Index: 6321533 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.9135. Min Act: -0.1700
Data Index: 1451751 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.8979. Min Act: -0.1700
Data Index: 6644133 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.8822. Min Act: -0.1700
Data Index: 999186 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.8979. Min Act: -0.1700
Data Index: 3880517 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.8510. Min Act: -0.1700
Data Index: 6561222 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.8510. Min Act: -0.1700
Data Index: 3678615 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.7884. Min Act: -0.1700
Data Index: 685427 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.7884. Min Act: -0.1700
Data Index: 7829893 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.7884. Min Act: -0.1700
Data Index: 2021722 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.7884. Min Act: -0.1700
Data Index: 4349457 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3199. Min Range: -4.3199
Max Act: 3.7728. Min Act: -0.1700
Data Index: 8365651 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19