Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3711 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.9990. Min Act: -0.1700
Data Index: 6322980 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.9990. Min Act: -0.1700
Data Index: 7485567 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.9990. Min Act: -0.1700
Data Index: 6380712 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.9365. Min Act: -0.1700
Data Index: 5157312 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.8740. Min Act: -0.1700
Data Index: 1384363 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.8740. Min Act: -0.1700
Data Index: 4365535 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.8115. Min Act: -0.1700
Data Index: 8629293 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.8115. Min Act: -0.1700
Data Index: 5845358 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.7490. Min Act: -0.1700
Data Index: 3063411 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.7490. Min Act: -0.1700
Data Index: 6912026 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.7490. Min Act: -0.1700
Data Index: 199793 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.7490. Min Act: -0.1700
Data Index: 6834666 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.7490. Min Act: -0.1700
Data Index: 1128839 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.7490. Min Act: -0.1700
Data Index: 723284 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.6865. Min Act: -0.1700
Data Index: 260222 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.6865. Min Act: -0.1700
Data Index: 8558121 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.6240. Min Act: -0.1700
Data Index: 2802760 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.6240. Min Act: -0.1700
Data Index: 4504199 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.5615. Min Act: -0.1700
Data Index: 7247963 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9990. Min Range: -8.9990
Max Act: 8.6240. Min Act: -0.1700
Data Index: 5773789 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19