Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2653 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.5220. Min Act: -0.1700
Data Index: 5218061 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.3032. Min Act: -0.1700
Data Index: 1251387 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.3032. Min Act: -0.1700
Data Index: 2830505 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.2720. Min Act: -0.1700
Data Index: 6650763 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1782. Min Act: -0.1700
Data Index: 7940058 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1782. Min Act: -0.1700
Data Index: 3038461 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1470. Min Act: -0.1700
Data Index: 3267038 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1470. Min Act: -0.1700
Data Index: 7849963 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.1157. Min Act: -0.1700
Data Index: 1084170 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0845. Min Act: -0.1700
Data Index: 2201955 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0532. Min Act: -0.1700
Data Index: 7613280 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3245129 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0532. Min Act: -0.1700
Data Index: 2837381 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0532. Min Act: -0.1700
Data Index: 1169136 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0220. Min Act: -0.1700
Data Index: 2881236 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9907. Min Act: -0.1700
Data Index: 656739 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5220. Min Range: -6.5220
Max Act: 6.0220. Min Act: -0.1700
Data Index: 722749 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9595. Min Act: -0.1700
Data Index: 306972 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9595. Min Act: -0.1700
Data Index: 1440690 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5220. Min Range: -6.5220
Max Act: 5.9282. Min Act: -0.1700
Data Index: 6941805 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19