Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4668 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8887. Min Act: -0.1700
Data Index: 2664 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8887. Min Act: -0.1700
Data Index: 2985846 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8728. Min Act: -0.1700
Data Index: 5842323 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8728. Min Act: -0.1700
Data Index: 419425 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8569. Min Act: -0.1700
Data Index: 2387825 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8569. Min Act: -0.1700
Data Index: 3853666 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8410. Min Act: -0.1700
Data Index: 525133 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8251. Min Act: -0.1700
Data Index: 8370289 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8410. Min Act: -0.1700
Data Index: 1086547 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.8092. Min Act: -0.1700
Data Index: 5689812 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7774. Min Act: -0.1700
Data Index: 7665576 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7774. Min Act: -0.1700
Data Index: 1084013 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7774. Min Act: -0.1700
Data Index: 4021951 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7774. Min Act: -0.1700
Data Index: 1109935 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7774. Min Act: -0.1700
Data Index: 7525296 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7614. Min Act: -0.1700
Data Index: 7687515 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7614. Min Act: -0.1700
Data Index: 974945 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7455. Min Act: -0.1700
Data Index: 7790824 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7135. Min Act: -0.1700
Data Index: 5450106 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8887. Min Range: -2.8887
Max Act: 2.7135. Min Act: -0.1700
Data Index: 3670128 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19