Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 564 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.2889. Min Act: -0.1700
Data Index: 2576949 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.2264. Min Act: -0.1700
Data Index: 233201 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.2264. Min Act: -0.1700
Data Index: 2447593 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.1951. Min Act: -0.1700
Data Index: 6935920 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.1951. Min Act: -0.1700
Data Index: 5467138 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.1639. Min Act: -0.1700
Data Index: 7805414 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.1013. Min Act: -0.1700
Data Index: 7926082 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.1326. Min Act: -0.1700
Data Index: 3703473 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0701. Min Act: -0.1700
Data Index: 4170956 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.1013. Min Act: -0.1700
Data Index: 6922237 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0701. Min Act: -0.1700
Data Index: 7864074 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0701. Min Act: -0.1700
Data Index: 4256461 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0701. Min Act: -0.1700
Data Index: 8672502 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0701. Min Act: -0.1700
Data Index: 6582226 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.1013. Min Act: -0.1700
Data Index: 5467478 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0701. Min Act: -0.1700
Data Index: 4323372 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0701. Min Act: -0.1700
Data Index: 1722099 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0388. Min Act: -0.1700
Data Index: 6899555 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0388. Min Act: -0.1700
Data Index: 180649 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2889. Min Range: -4.2889
Max Act: 4.0388. Min Act: -0.1700
Data Index: 6931401 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19