Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5640 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.5532. Min Act: -0.1700
Data Index: 3663926 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.5532. Min Act: -0.1700
Data Index: 646880 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.5220. Min Act: -0.1700
Data Index: 7201192 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.4907. Min Act: -0.1700
Data Index: 6799473 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.4282. Min Act: -0.1700
Data Index: 5878405 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.2407. Min Act: -0.1700
Data Index: 5039434 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.2407. Min Act: -0.1700
Data Index: 2156391 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.1782. Min Act: -0.1700
Data Index: 522668 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.1470. Min Act: -0.1700
Data Index: 1070191 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.1470. Min Act: -0.1700
Data Index: 1903337 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.1782. Min Act: -0.1700
Data Index: 6914280 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.1157. Min Act: -0.1700
Data Index: 3512177 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.1157. Min Act: -0.1700
Data Index: 672278 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.0532. Min Act: -0.1700
Data Index: 4256561 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.0220. Min Act: -0.1700
Data Index: 7661015 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5532. Min Range: -7.5532
Max Act: 6.9907. Min Act: -0.1700
Data Index: 6612684 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5532. Min Range: -7.5532
Max Act: 7.0220. Min Act: -0.1700
Data Index: 8450064 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5532. Min Range: -7.5532
Max Act: 6.9907. Min Act: -0.1700
Data Index: 4414140 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5532. Min Range: -7.5532
Max Act: 6.9907. Min Act: -0.1700
Data Index: 3771083 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5532. Min Range: -7.5532
Max Act: 6.9907. Min Act: -0.1700
Data Index: 7497735 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19