Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1243 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1099. Min Range: -8.1099
Max Act: 8.1099. Min Act: -0.1700
Data Index: 5712275 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.9224. Min Act: -0.1700
Data Index: 1015765 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.8599. Min Act: -0.1700
Data Index: 8239403 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.7974. Min Act: -0.1700
Data Index: 7916876 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.6724. Min Act: -0.1700
Data Index: 8008292 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.6411. Min Act: -0.1700
Data Index: 4915674 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.6411. Min Act: -0.1700
Data Index: 8303105 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.5474. Min Act: -0.1700
Data Index: 1676620 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.5161. Min Act: -0.1700
Data Index: 3652567 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.5474. Min Act: -0.1700
Data Index: 8277548 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.5474. Min Act: -0.1700
Data Index: 3620306 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.4849. Min Act: -0.1700
Data Index: 4258259 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.4536. Min Act: -0.1700
Data Index: 1865382 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.4536. Min Act: -0.1700
Data Index: 8480139 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.4536. Min Act: -0.1700
Data Index: 8698988 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.4224. Min Act: -0.1700
Data Index: 4111867 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.4224. Min Act: -0.1700
Data Index: 4994837 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.3911. Min Act: -0.1700
Data Index: 7879668 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.4224. Min Act: -0.1700
Data Index: 4557887 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1099. Min Range: -8.1099
Max Act: 7.3911. Min Act: -0.1700
Data Index: 6809227 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19