Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 275 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.9100. Min Act: -0.1700
Data Index: 5350620 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.8475. Min Act: -0.1700
Data Index: 1023591 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.7538. Min Act: -0.1700
Data Index: 6557426 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.7225. Min Act: -0.1700
Data Index: 4905601 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6913. Min Act: -0.1700
Data Index: 8440684 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6600. Min Act: -0.1700
Data Index: 8552621 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6600. Min Act: -0.1700
Data Index: 1013612 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 3760450 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 6958087 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 2060042 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 4024068 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5663. Min Act: -0.1700
Data Index: 1836752 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5663. Min Act: -0.1700
Data Index: 5350622 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5663. Min Act: -0.1700
Data Index: 320721 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5663. Min Act: -0.1700
Data Index: 1403556 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5663. Min Act: -0.1700
Data Index: 4760278 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5663. Min Act: -0.1700
Data Index: 3747894 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5038. Min Act: -0.1700
Data Index: 4760277 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5038. Min Act: -0.1700
Data Index: 603840 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5038. Min Act: -0.1700
Data Index: 298858 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19