Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 285 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.6788. Min Act: -0.1700
Data Index: 7872110 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.6788. Min Act: -0.1699
Data Index: 910132 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.6788. Min Act: -0.1696
Data Index: 1505295 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.6091. Min Act: -0.1700
Data Index: 1301461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5654. Min Act: -0.1603
Data Index: 5023586 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5567. Min Act: -0.1699
Data Index: 866534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5567. Min Act: -0.1696
Data Index: 7817549 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5654. Min Act: -0.1699
Data Index: 7788599 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5479. Min Act: -0.1700
Data Index: 5277920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5479. Min Act: -0.1642
Data Index: 8185747 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5392. Min Act: -0.1696
Data Index: 2387103 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5392. Min Act: -0.1700
Data Index: 623507 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5392. Min Act: -0.1700
Data Index: 1505294 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5304. Min Act: -0.1693
Data Index: 2819027 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5216. Min Act: -0.1700
Data Index: 2121307 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5304. Min Act: -0.1700
Data Index: 115913 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5129. Min Act: -0.1699
Data Index: 552700 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5129. Min Act: -0.1700
Data Index: 2399924 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5041. Min Act: -0.1697
Data Index: 4803870 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6788. Min Range: -1.6788
Max Act: 1.5129. Min Act: -0.1700
Data Index: 7266494 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19