Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.5287. Min Act: -0.1700
Data Index: 1721063 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.4975. Min Act: -0.1700
Data Index: 8620090 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.4975. Min Act: -0.1700
Data Index: 3302330 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.4350. Min Act: -0.1700
Data Index: 3784124 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.4037. Min Act: -0.1700
Data Index: 1827106 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.4037. Min Act: -0.1700
Data Index: 3898329 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.4037. Min Act: -0.1700
Data Index: 8210368 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.3412. Min Act: -0.1700
Data Index: 4029296 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.3100. Min Act: -0.1700
Data Index: 734501 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.3100. Min Act: -0.1700
Data Index: 5662337 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.2787. Min Act: -0.1700
Data Index: 6555171 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.2162. Min Act: -0.1700
Data Index: 3451232 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.2475. Min Act: -0.1700
Data Index: 2216465 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.2475. Min Act: -0.1700
Data Index: 4991660 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.1850. Min Act: -0.1700
Data Index: 1480393 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.1537. Min Act: -0.1700
Data Index: 7333139 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.1537. Min Act: -0.1700
Data Index: 1134609 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.0912. Min Act: -0.1700
Data Index: 2106938 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.0912. Min Act: -0.1700
Data Index: 5681857 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5287. Min Range: -5.5287
Max Act: 5.0912. Min Act: -0.1700
Data Index: 1699917 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19