Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0878. Min Range: -7.0878
Max Act: 7.0878. Min Act: -0.1700
Data Index: 3913353 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0878. Min Range: -7.0878
Max Act: 7.0253. Min Act: -0.1700
Data Index: 2839555 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.9316. Min Act: -0.1700
Data Index: 699838 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.9316. Min Act: -0.1700
Data Index: 8069516 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.8378. Min Act: -0.1700
Data Index: 1146365 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.7753. Min Act: -0.1700
Data Index: 862631 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.7441. Min Act: -0.1700
Data Index: 947175 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.7128. Min Act: -0.1700
Data Index: 313487 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.7128. Min Act: -0.1700
Data Index: 7762450 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6816. Min Act: -0.1700
Data Index: 5492161 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6191. Min Act: -0.1700
Data Index: 4155670 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.6191. Min Act: -0.1700
Data Index: 1730045 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5878. Min Act: -0.1700
Data Index: 8413566 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5566. Min Act: -0.1700
Data Index: 1387120 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5566. Min Act: -0.1700
Data Index: 8542767 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5566. Min Act: -0.1700
Data Index: 2163782 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5566. Min Act: -0.1700
Data Index: 6924803 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5253. Min Act: -0.1700
Data Index: 4804298 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5253. Min Act: -0.1700
Data Index: 3952253 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0878. Min Range: -7.0878
Max Act: 6.5253. Min Act: -0.1700
Data Index: 4732546 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19