Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.7475. Min Act: -0.1698
Data Index: 3305831 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6836. Min Act: -0.1697
Data Index: 8282851 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6836. Min Act: -0.1700
Data Index: 7156276 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6515. Min Act: -0.1700
Data Index: 5066055 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6355. Min Act: -0.1700
Data Index: 5867258 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6355. Min Act: -0.1700
Data Index: 4866524 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6515. Min Act: -0.1698
Data Index: 5943640 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6515. Min Act: -0.1700
Data Index: 8351900 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6355. Min Act: -0.1700
Data Index: 2748308 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6194. Min Act: -0.1700
Data Index: 8807487 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6355. Min Act: -0.1697
Data Index: 2706077 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.5872. Min Act: -0.1700
Data Index: 4866526 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6033. Min Act: -0.1700
Data Index: 5059796 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.6033. Min Act: -0.1700
Data Index: 506366 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.5872. Min Act: -0.1700
Data Index: 5937526 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.5711. Min Act: -0.1700
Data Index: 8438128 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.5872. Min Act: -0.1681
Data Index: 8831621 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.5872. Min Act: -0.1700
Data Index: 4062498 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.5550. Min Act: -0.1700
Data Index: 5392949 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7475. Min Range: -2.7475
Max Act: 2.5711. Min Act: -0.1700
Data Index: 8252644 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19