Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.4663. Min Act: -0.1700
Data Index: 5889321 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.4038. Min Act: -0.1700
Data Index: 4722519 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.3101. Min Act: -0.1700
Data Index: 1186655 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.3101. Min Act: -0.1700
Data Index: 2629810 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.2788. Min Act: -0.1700
Data Index: 5703403 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.2476. Min Act: -0.1700
Data Index: 4459469 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.2476. Min Act: -0.1700
Data Index: 1684662 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.2163. Min Act: -0.1700
Data Index: 5062936 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 3143513 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 3992288 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 8315557 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 8599305 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 7897903 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 1866085 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1538. Min Act: -0.1700
Data Index: 5373859 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 7405187 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1538. Min Act: -0.1700
Data Index: 8043768 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1538. Min Act: -0.1700
Data Index: 479500 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1538. Min Act: -0.1700
Data Index: 2592473 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4663. Min Range: -4.4663
Max Act: 4.1851. Min Act: -0.1700
Data Index: 6718035 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19