Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1403 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.5474. Min Act: -0.1700
Data Index: 2491940 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.3911. Min Act: -0.1700
Data Index: 7705363 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.3286. Min Act: -0.1700
Data Index: 906917 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.2661. Min Act: -0.1700
Data Index: 894200 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.2036. Min Act: -0.1700
Data Index: 994103 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.1724. Min Act: -0.1700
Data Index: 7330664 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.1411. Min Act: -0.1700
Data Index: 7709889 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.1411. Min Act: -0.1700
Data Index: 1446542 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.1411. Min Act: -0.1700
Data Index: 1061995 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.1411. Min Act: -0.1700
Data Index: 3227679 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.1411. Min Act: -0.1700
Data Index: 3717559 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.1099. Min Act: -0.1700
Data Index: 3838423 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.0786. Min Act: -0.1700
Data Index: 4473580 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.0786. Min Act: -0.1700
Data Index: 2162189 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.0786. Min Act: -0.1700
Data Index: 4181713 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.0786. Min Act: -0.1700
Data Index: 6475185 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.0474. Min Act: -0.1700
Data Index: 7454797 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5474. Min Range: -6.5474
Max Act: 6.0161. Min Act: -0.1700
Data Index: 7508259 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5474. Min Range: -6.5474
Max Act: 5.9849. Min Act: -0.1700
Data Index: 3931699 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5474. Min Range: -6.5474
Max Act: 5.9849. Min Act: -0.1700
Data Index: 5745895 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19