Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.6131. Min Act: -0.1700
Data Index: 6672713 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.4881. Min Act: -0.1700
Data Index: 2526796 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.5193. Min Act: -0.1700
Data Index: 6546888 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.4568. Min Act: -0.1700
Data Index: 422957 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.3631. Min Act: -0.1700
Data Index: 7914850 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.3631. Min Act: -0.1700
Data Index: 5055711 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.3006. Min Act: -0.1700
Data Index: 5461432 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2693. Min Act: -0.1700
Data Index: 8202169 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.3006. Min Act: -0.1700
Data Index: 3347723 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2381. Min Act: -0.1700
Data Index: 4734832 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2693. Min Act: -0.1700
Data Index: 2738915 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2693. Min Act: -0.1700
Data Index: 3187281 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2381. Min Act: -0.1700
Data Index: 2801880 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2381. Min Act: -0.1700
Data Index: 4086550 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2068. Min Act: -0.1700
Data Index: 4190598 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.1756. Min Act: -0.1700
Data Index: 3935976 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.2068. Min Act: -0.1700
Data Index: 7848937 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.1756. Min Act: -0.1700
Data Index: 5765166 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.1756. Min Act: -0.1700
Data Index: 107950 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6131. Min Range: -5.6131
Max Act: 5.1756. Min Act: -0.1700
Data Index: 5320369 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19