Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4780 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1294. Min Range: -6.1294
Max Act: 6.1294. Min Act: -0.1700
Data Index: 7811901 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.8481. Min Act: -0.1700
Data Index: 8676609 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.6294. Min Act: -0.1700
Data Index: 1537237 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.6606. Min Act: -0.1700
Data Index: 2086290 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.6294. Min Act: -0.1700
Data Index: 8555652 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.5669. Min Act: -0.1700
Data Index: 4546057 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.5669. Min Act: -0.1700
Data Index: 865054 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.5356. Min Act: -0.1700
Data Index: 5440843 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.5356. Min Act: -0.1700
Data Index: 6256206 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.5044. Min Act: -0.1700
Data Index: 844024 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.5044. Min Act: -0.1700
Data Index: 6094191 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.4731. Min Act: -0.1700
Data Index: 2064529 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.4419. Min Act: -0.1700
Data Index: 3977705 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.4419. Min Act: -0.1700
Data Index: 7070417 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.4419. Min Act: -0.1700
Data Index: 8431361 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.4419. Min Act: -0.1700
Data Index: 4210249 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.3794. Min Act: -0.1700
Data Index: 7811953 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.3794. Min Act: -0.1700
Data Index: 3592481 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.3794. Min Act: -0.1700
Data Index: 2143098 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1294. Min Range: -6.1294
Max Act: 5.3481. Min Act: -0.1700
Data Index: 5603237 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19