Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 626 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.4176. Min Act: -0.1700
Data Index: 153728 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.3239. Min Act: -0.1700
Data Index: 922473 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.3239. Min Act: -0.1700
Data Index: 4753591 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2926. Min Act: -0.1700
Data Index: 3600195 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2926. Min Act: -0.1700
Data Index: 5929153 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2614. Min Act: -0.1700
Data Index: 7753786 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2614. Min Act: -0.1700
Data Index: 5166093 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2614. Min Act: -0.1700
Data Index: 1970078 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2301. Min Act: -0.1700
Data Index: 4988318 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1989. Min Act: -0.1700
Data Index: 4367380 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2301. Min Act: -0.1700
Data Index: 8351340 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1989. Min Act: -0.1700
Data Index: 2534614 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1676. Min Act: -0.1700
Data Index: 2029688 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1989. Min Act: -0.1700
Data Index: 7453314 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1989. Min Act: -0.1700
Data Index: 7329689 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1989. Min Act: -0.1700
Data Index: 1997462 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1989. Min Act: -0.1700
Data Index: 2354493 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1989. Min Act: -0.1700
Data Index: 5865774 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.1676. Min Act: -0.1700
Data Index: 592343 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4176. Min Range: -4.4176
Max Act: 4.2301. Min Act: -0.1700
Data Index: 4630490 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19