Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.1720. Min Act: -0.1700
Data Index: 7761504 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.1408. Min Act: -0.1700
Data Index: 3411119 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.1095. Min Act: -0.1700
Data Index: 1934328 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.0158. Min Act: -0.1700
Data Index: 548856 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.0158. Min Act: -0.1700
Data Index: 7460398 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.0158. Min Act: -0.1700
Data Index: 7384280 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9845. Min Act: -0.1700
Data Index: 1536611 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.0783. Min Act: -0.1700
Data Index: 8254018 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9845. Min Act: -0.1700
Data Index: 6806479 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1720. Min Range: -5.1720
Max Act: 5.0158. Min Act: -0.1700
Data Index: 4343268 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9845. Min Act: -0.1700
Data Index: 8039561 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9845. Min Act: -0.1699
Data Index: 4528980 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9845. Min Act: -0.1700
Data Index: 5333268 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9220. Min Act: -0.1700
Data Index: 5968713 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9533. Min Act: -0.1700
Data Index: 2131071 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9533. Min Act: -0.1700
Data Index: 5780519 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9533. Min Act: -0.1700
Data Index: 3475279 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9220. Min Act: -0.1700
Data Index: 851873 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.8908. Min Act: -0.1700
Data Index: 6692591 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1720. Min Range: -5.1720
Max Act: 4.9220. Min Act: -0.1700
Data Index: 5615135 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19