Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1596. Min Range: -9.1596
Max Act: 9.1596. Min Act: -0.1700
Data Index: 4889229 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1596. Min Range: -9.1596
Max Act: 8.0659. Min Act: -0.1700
Data Index: 8404858 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1596. Min Range: -9.1596
Max Act: 8.0346. Min Act: -0.1700
Data Index: 1359794 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.9721. Min Act: -0.1700
Data Index: 3912658 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.9721. Min Act: -0.1700
Data Index: 6510977 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.9096. Min Act: -0.1700
Data Index: 1636593 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.8784. Min Act: -0.1700
Data Index: 651637 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.8159. Min Act: -0.1700
Data Index: 4105150 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.8159. Min Act: -0.1700
Data Index: 7964352 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.8159. Min Act: -0.1700
Data Index: 7418893 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.7846. Min Act: -0.1700
Data Index: 3065262 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.7534. Min Act: -0.1700
Data Index: 8074610 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.6909. Min Act: -0.1700
Data Index: 2201827 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.7221. Min Act: -0.1700
Data Index: 589480 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.6909. Min Act: -0.1700
Data Index: 4821400 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.6909. Min Act: -0.1700
Data Index: 2789914 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.7221. Min Act: -0.1700
Data Index: 2254836 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.6596. Min Act: -0.1700
Data Index: 5453191 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.6596. Min Act: -0.1700
Data Index: 1696875 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1596. Min Range: -9.1596
Max Act: 7.6596. Min Act: -0.1700
Data Index: 3548433 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19