Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2076 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.3480. Min Act: -0.1700
Data Index: 27422 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.3167. Min Act: -0.1700
Data Index: 4889863 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.2855. Min Act: -0.1700
Data Index: 5958325 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.2230. Min Act: -0.1700
Data Index: 4345002 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.2230. Min Act: -0.1700
Data Index: 410801 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.1917. Min Act: -0.1700
Data Index: 4922475 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.1292. Min Act: -0.1700
Data Index: 6486286 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0667. Min Act: -0.1700
Data Index: 5369548 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0667. Min Act: -0.1700
Data Index: 3743110 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0667. Min Act: -0.1700
Data Index: 5207885 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0355. Min Act: -0.1700
Data Index: 6171457 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0042. Min Act: -0.1700
Data Index: 5812873 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0042. Min Act: -0.1700
Data Index: 7025606 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0042. Min Act: -0.1700
Data Index: 5317833 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0042. Min Act: -0.1700
Data Index: 3373954 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9730. Min Act: -0.1700
Data Index: 2029126 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9730. Min Act: -0.1700
Data Index: 1682009 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9730. Min Act: -0.1700
Data Index: 8726572 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9730. Min Act: -0.1700
Data Index: 986735 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9730. Min Act: -0.1700
Data Index: 2371354 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19