Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0556. Min Range: -3.0556
Max Act: 3.0556. Min Act: -0.1700
Data Index: 3060866 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0556. Min Range: -3.0556
Max Act: 3.0556. Min Act: -0.1700
Data Index: 7076672 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0556. Min Range: -3.0556
Max Act: 3.0241. Min Act: -0.1700
Data Index: 5119466 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0556. Min Range: -3.0556
Max Act: 3.0399. Min Act: -0.1700
Data Index: 3997640 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0556. Min Range: -3.0556
Max Act: 3.0241. Min Act: -0.1700
Data Index: 2691685 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0556. Min Range: -3.0556
Max Act: 3.0083. Min Act: -0.1700
Data Index: 8659861 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9925. Min Act: -0.1700
Data Index: 4637376 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9925. Min Act: -0.1700
Data Index: 3680866 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9767. Min Act: -0.1700
Data Index: 352181 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9767. Min Act: -0.1700
Data Index: 705188 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9767. Min Act: -0.1700
Data Index: 1872601 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9608. Min Act: -0.1700
Data Index: 469647 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9608. Min Act: -0.1700
Data Index: 7175271 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9608. Min Act: -0.1700
Data Index: 5209893 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9450. Min Act: -0.1700
Data Index: 1280042 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9450. Min Act: -0.1700
Data Index: 5282998 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9450. Min Act: -0.1700
Data Index: 460362 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9767. Min Act: -0.1700
Data Index: 1306804 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9608. Min Act: -0.1700
Data Index: 6319218 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0556. Min Range: -3.0556
Max Act: 2.9608. Min Act: -0.1700
Data Index: 1008080 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19