Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.5291. Min Act: -0.1700
Data Index: 886640 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.2478. Min Act: -0.1700
Data Index: 6948338 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.2478. Min Act: -0.1700
Data Index: 3314229 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.2166. Min Act: -0.1700
Data Index: 6638676 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.2166. Min Act: -0.1700
Data Index: 654512 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.1540. Min Act: -0.1700
Data Index: 6259329 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.1540. Min Act: -0.1700
Data Index: 7561160 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.1228. Min Act: -0.1700
Data Index: 5579662 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.0603. Min Act: -0.1700
Data Index: 2566581 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5291. Min Range: -4.5291
Max Act: 4.0603. Min Act: -0.1700
Data Index: 5470881 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.9665. Min Act: -0.1700
Data Index: 1416250 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.9978. Min Act: -0.1700
Data Index: 138257 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.9978. Min Act: -0.1700
Data Index: 1560333 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.9352. Min Act: -0.1700
Data Index: 954069 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.9352. Min Act: -0.1700
Data Index: 4004580 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.9352. Min Act: -0.1700
Data Index: 3165330 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.8727. Min Act: -0.1700
Data Index: 3223819 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.8414. Min Act: -0.1700
Data Index: 4010927 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.8727. Min Act: -0.1700
Data Index: 3669251 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5291. Min Range: -4.5291
Max Act: 3.8727. Min Act: -0.1700
Data Index: 2936282 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19