Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2321 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.3533. Min Act: -0.1700
Data Index: 6935446 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2277. Min Act: -0.1700
Data Index: 1114534 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2591. Min Act: -0.1700
Data Index: 368409 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2277. Min Act: -0.1700
Data Index: 1184080 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2277. Min Act: -0.1700
Data Index: 1234620 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.2277. Min Act: -0.1700
Data Index: 5235452 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1805. Min Act: -0.1700
Data Index: 6880367 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1963. Min Act: -0.1700
Data Index: 5618241 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1648. Min Act: -0.1700
Data Index: 7403477 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1805. Min Act: -0.1700
Data Index: 1731842 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1805. Min Act: -0.1700
Data Index: 2541818 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1805. Min Act: -0.1700
Data Index: 801277 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1648. Min Act: -0.1700
Data Index: 6544148 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1648. Min Act: -0.1700
Data Index: 8548077 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1805. Min Act: -0.1700
Data Index: 8594087 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1333. Min Act: -0.1700
Data Index: 7495426 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1491. Min Act: -0.1700
Data Index: 2793496 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1333. Min Act: -0.1700
Data Index: 4526730 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1491. Min Act: -0.1700
Data Index: 1422022 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3533. Min Range: -3.3533
Max Act: 3.1333. Min Act: -0.1700
Data Index: 2402703 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19