Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1540. Min Range: -5.1540
Max Act: 5.1540. Min Act: -0.1700
Data Index: 2087460 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.9352. Min Act: -0.1700
Data Index: 1112367 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.9040. Min Act: -0.1700
Data Index: 591004 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.8727. Min Act: -0.1700
Data Index: 1062182 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.8102. Min Act: -0.1700
Data Index: 1670445 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.8102. Min Act: -0.1700
Data Index: 4882462 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.7790. Min Act: -0.1700
Data Index: 7861255 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6852. Min Act: -0.1700
Data Index: 6777420 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6852. Min Act: -0.1700
Data Index: 3164480 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6852. Min Act: -0.1700
Data Index: 3211728 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6540. Min Act: -0.1700
Data Index: 8000858 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6540. Min Act: -0.1700
Data Index: 6677455 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.5915. Min Act: -0.1700
Data Index: 8276273 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6227. Min Act: -0.1700
Data Index: 5916056 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.5915. Min Act: -0.1700
Data Index: 1665488 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6227. Min Act: -0.1700
Data Index: 3810705 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.5915. Min Act: -0.1700
Data Index: 5399110 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.5915. Min Act: -0.1700
Data Index: 5034610 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.6227. Min Act: -0.1700
Data Index: 6996255 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1540. Min Range: -5.1540
Max Act: 4.5915. Min Act: -0.1700
Data Index: 1440005 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19