Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6033 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.5318. Min Act: -0.1700
Data Index: 5448171 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.5006. Min Act: -0.1700
Data Index: 425726 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.5006. Min Act: -0.1700
Data Index: 7935444 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.5006. Min Act: -0.1700
Data Index: 4552994 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.4693. Min Act: -0.1700
Data Index: 1978885 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.4381. Min Act: -0.1700
Data Index: 8311542 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.4068. Min Act: -0.1700
Data Index: 6896538 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.4068. Min Act: -0.1700
Data Index: 2321042 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.4068. Min Act: -0.1700
Data Index: 3831461 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.4068. Min Act: -0.1700
Data Index: 266890 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3756. Min Act: -0.1700
Data Index: 7678268 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3756. Min Act: -0.1700
Data Index: 5871846 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3756. Min Act: -0.1700
Data Index: 266894 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3131. Min Act: -0.1700
Data Index: 266892 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3443. Min Act: -0.1700
Data Index: 4151055 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3131. Min Act: -0.1700
Data Index: 5369644 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3131. Min Act: -0.1700
Data Index: 4675029 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3131. Min Act: -0.1700
Data Index: 6188272 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.3131. Min Act: -0.1700
Data Index: 1813555 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5318. Min Range: -4.5318
Max Act: 4.2818. Min Act: -0.1700
Data Index: 5961768 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19