Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4432 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.6629. Min Act: -0.1700
Data Index: 515983 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.5691. Min Act: -0.1700
Data Index: 3437772 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.5379. Min Act: -0.1700
Data Index: 4770657 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.5379. Min Act: -0.1700
Data Index: 5083181 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.5379. Min Act: -0.1700
Data Index: 3588671 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.5379. Min Act: -0.1700
Data Index: 697545 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.5066. Min Act: -0.1700
Data Index: 2991247 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.4754. Min Act: -0.1700
Data Index: 4301800 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.4754. Min Act: -0.1700
Data Index: 4157816 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.4129. Min Act: -0.1700
Data Index: 2022886 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.4129. Min Act: -0.1700
Data Index: 8021935 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.4129. Min Act: -0.1700
Data Index: 5758762 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3816. Min Act: -0.1700
Data Index: 4410223 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3816. Min Act: -0.1700
Data Index: 5095016 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3816. Min Act: -0.1700
Data Index: 8591946 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3816. Min Act: -0.1700
Data Index: 2484120 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3816. Min Act: -0.1700
Data Index: 8260481 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3504. Min Act: -0.1700
Data Index: 5644168 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3504. Min Act: -0.1700
Data Index: 2708413 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6629. Min Range: -5.6629
Max Act: 5.3504. Min Act: -0.1700
Data Index: 2847659 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19