Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 768 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.1692. Min Range: -9.1692
Max Act: 9.1692. Min Act: -0.1700
Data Index: 3356648 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1692. Min Range: -9.1692
Max Act: 9.1067. Min Act: -0.1700
Data Index: 3393365 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1692. Min Range: -9.1692
Max Act: 9.1067. Min Act: -0.1700
Data Index: 8482259 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.8567. Min Act: -0.1700
Data Index: 2887478 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.7942. Min Act: -0.1700
Data Index: 1120971 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.7317. Min Act: -0.1700
Data Index: 4943752 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.7942. Min Act: -0.1700
Data Index: 7495958 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.7942. Min Act: -0.1700
Data Index: 1999377 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.7317. Min Act: -0.1700
Data Index: 4064593 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.7317. Min Act: -0.1700
Data Index: 3245904 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.6692. Min Act: -0.1700
Data Index: 3658659 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.5442. Min Act: -0.1700
Data Index: 2440434 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.6067. Min Act: -0.1700
Data Index: 2170293 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.5442. Min Act: -0.1700
Data Index: 6522501 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.5442. Min Act: -0.1700
Data Index: 2067147 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.5442. Min Act: -0.1700
Data Index: 970932 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.6067. Min Act: -0.1700
Data Index: 3534230 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.6067. Min Act: -0.1700
Data Index: 72908 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.5442. Min Act: -0.1700
Data Index: 2376663 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1692. Min Range: -9.1692
Max Act: 8.4817. Min Act: -0.1700
Data Index: 1430573 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19