Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1481 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.8766. Min Act: -0.1700
Data Index: 229711 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.8141. Min Act: -0.1700
Data Index: 5994816 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.6891. Min Act: -0.1700
Data Index: 8181290 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.6266. Min Act: -0.1700
Data Index: 5566798 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.6266. Min Act: -0.1700
Data Index: 6331280 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.5641. Min Act: -0.1700
Data Index: 8715685 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.5641. Min Act: -0.1700
Data Index: 4689698 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.5016. Min Act: -0.1700
Data Index: 8240493 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.4391. Min Act: -0.1700
Data Index: 6958695 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.4391. Min Act: -0.1700
Data Index: 3886408 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.4391. Min Act: -0.1700
Data Index: 1964764 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.4391. Min Act: -0.1700
Data Index: 8721138 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.3766. Min Act: -0.1700
Data Index: 2273301 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.3766. Min Act: -0.1700
Data Index: 7477480 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.2516. Min Act: -0.1700
Data Index: 559004 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.2516. Min Act: -0.1700
Data Index: 1793984 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.1891. Min Act: -0.1700
Data Index: 8721148 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.2516. Min Act: -0.1700
Data Index: 1550691 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.2516. Min Act: -0.1700
Data Index: 2641454 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8766. Min Range: -10.8766
Max Act: 10.1891. Min Act: -0.1700
Data Index: 6646693 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19