Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2511 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2023. Min Range: -4.2023
Max Act: 4.2023. Min Act: -0.1700
Data Index: 2817075 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.9835. Min Act: -0.1700
Data Index: 6090381 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.9835. Min Act: -0.1700
Data Index: 118728 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.9835. Min Act: -0.1700
Data Index: 7178031 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.9522. Min Act: -0.1700
Data Index: 5535725 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.9209. Min Act: -0.1700
Data Index: 1819714 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.9209. Min Act: -0.1700
Data Index: 8671963 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6793839 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7911953 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7162687 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8584. Min Act: -0.1700
Data Index: 343891 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8584. Min Act: -0.1700
Data Index: 7205527 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8584. Min Act: -0.1700
Data Index: 2555273 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8584. Min Act: -0.1700
Data Index: 7242186 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8584. Min Act: -0.1700
Data Index: 5223840 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8584. Min Act: -0.1700
Data Index: 4753708 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8271. Min Act: -0.1700
Data Index: 3886140 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.7959. Min Act: -0.1700
Data Index: 4842083 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8271. Min Act: -0.1700
Data Index: 4186444 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2023. Min Range: -4.2023
Max Act: 3.8271. Min Act: -0.1700
Data Index: 4880164 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19