Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.1559. Min Act: -0.1700
Data Index: 1791448 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.1401. Min Act: -0.1700
Data Index: 7048331 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.1401. Min Act: -0.1700
Data Index: 2424757 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.1086. Min Act: -0.1700
Data Index: 6337806 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0929. Min Act: -0.1700
Data Index: 5283193 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0929. Min Act: -0.1700
Data Index: 365320 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0929. Min Act: -0.1700
Data Index: 6612644 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0929. Min Act: -0.1700
Data Index: 302714 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0929. Min Act: -0.1700
Data Index: 8396582 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0771. Min Act: -0.1700
Data Index: 594650 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0771. Min Act: -0.1700
Data Index: 265397 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0613. Min Act: -0.1700
Data Index: 1413647 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0298. Min Act: -0.1700
Data Index: 671246 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0455. Min Act: -0.1700
Data Index: 862123 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0455. Min Act: -0.1700
Data Index: 1600396 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0140. Min Act: -0.1700
Data Index: 8488798 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0298. Min Act: -0.1700
Data Index: 2405799 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0298. Min Act: -0.1700
Data Index: 4620702 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1559. Min Range: -3.1559
Max Act: 3.0298. Min Act: -0.1700
Data Index: 7347559 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1559. Min Range: -3.1559
Max Act: 2.9982. Min Act: -0.1700
Data Index: 6666979 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19