Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 768 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.4252. Min Act: -0.1700
Data Index: 3776241 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.3627. Min Act: -0.1700
Data Index: 1468024 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.3315. Min Act: -0.1700
Data Index: 1415390 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.3002. Min Act: -0.1700
Data Index: 4415490 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2690. Min Act: -0.1700
Data Index: 5586536 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2690. Min Act: -0.1700
Data Index: 4415503 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2690. Min Act: -0.1700
Data Index: 5969552 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 8371683 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2065. Min Act: -0.1700
Data Index: 6625736 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 425135 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 6206743 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 8714497 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 7076109 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1752. Min Act: -0.1700
Data Index: 2651672 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.2065. Min Act: -0.1700
Data Index: 1676234 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1440. Min Act: -0.1700
Data Index: 1521500 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1440. Min Act: -0.1700
Data Index: 8291461 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1127. Min Act: -0.1700
Data Index: 221914 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.0815. Min Act: -0.1700
Data Index: 4162210 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4252. Min Range: -5.4252
Max Act: 5.1127. Min Act: -0.1700
Data Index: 1322569 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19