Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0306. Min Range: -8.0306
Max Act: 8.0306. Min Act: -0.1700
Data Index: 8756355 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.1243. Min Act: -0.1700
Data Index: 1370831 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0306. Min Range: -8.0306
Max Act: 7.1556. Min Act: -0.1700
Data Index: 5473268 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0306. Min Range: -8.0306
Max Act: 7.0306. Min Act: -0.1700
Data Index: 5493134 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0306. Min Range: -8.0306
Max Act: 7.3431. Min Act: -0.1700
Data Index: 4796402 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0306. Min Range: -8.0306
Max Act: 7.5306. Min Act: -0.1700
Data Index: 4518316 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.5931. Min Act: -0.1700
Data Index: 5180349 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0306. Min Range: -8.0306
Max Act: 7.1556. Min Act: -0.1700
Data Index: 5562849 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0306. Min Range: -8.0306
Max Act: 7.4056. Min Act: -0.1700
Data Index: 6072909 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0306. Min Range: -8.0306
Max Act: 5.9681. Min Act: -0.1700
Data Index: 7445067 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0306. Min Range: -8.0306
Max Act: 7.3431. Min Act: -0.1700
Data Index: 4647167 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.9056. Min Act: -0.1700
Data Index: 5394527 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.9056. Min Act: -0.1700
Data Index: 5694446 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0306. Min Range: -8.0306
Max Act: 4.1868. Min Act: -0.1700
Data Index: 8678755 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.6868. Min Act: -0.1700
Data Index: 8317430 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.0931. Min Act: -0.1700
Data Index: 9996 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.9681. Min Act: -0.1700
Data Index: 1801294 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0306. Min Range: -8.0306
Max Act: 5.0306. Min Act: -0.1699
Data Index: 8142889 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.7806. Min Act: -0.1700
Data Index: 5692495 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0306. Min Range: -8.0306
Max Act: 6.9681. Min Act: -0.1700
Data Index: 1890507 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19