Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.7420. Min Act: -0.1700
Data Index: 7984689 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.4846. Min Act: -0.1700
Data Index: 6457772 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.3869. Min Act: -0.1700
Data Index: 3200417 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.3542. Min Act: -0.1700
Data Index: 7124277 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.3378. Min Act: -0.1700
Data Index: 34402 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.3214. Min Act: -0.1700
Data Index: 539905 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.3214. Min Act: -0.1700
Data Index: 3926702 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2885. Min Act: -0.1700
Data Index: 6738550 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2720. Min Act: -0.1700
Data Index: 171839 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2720. Min Act: -0.1700
Data Index: 2968790 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2720. Min Act: -0.1700
Data Index: 907487 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2555. Min Act: -0.1700
Data Index: 2656632 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2555. Min Act: -0.1700
Data Index: 2269748 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2555. Min Act: -0.1700
Data Index: 5382772 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2390. Min Act: -0.1700
Data Index: 5492307 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2390. Min Act: -0.1700
Data Index: 5454426 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2225. Min Act: -0.1700
Data Index: 449029 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2059. Min Act: -0.1700
Data Index: 4594978 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2059. Min Act: -0.1700
Data Index: 6530629 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7420. Min Range: -2.7420
Max Act: 2.2059. Min Act: -0.1700
Data Index: 5956479 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19