Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4394 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.9959. Min Act: -0.1700
Data Index: 6748304 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.9326. Min Act: -0.1700
Data Index: 6136839 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.9326. Min Act: -0.1700
Data Index: 4601141 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.9009. Min Act: -0.1700
Data Index: 1441984 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.9009. Min Act: -0.1700
Data Index: 639964 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8691. Min Act: -0.1700
Data Index: 8412679 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8691. Min Act: -0.1700
Data Index: 5325934 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8691. Min Act: -0.1700
Data Index: 3758412 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8691. Min Act: -0.1700
Data Index: 8039562 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8533. Min Act: -0.1700
Data Index: 923376 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8215. Min Act: -0.1700
Data Index: 5991716 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8215. Min Act: -0.1700
Data Index: 417296 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8215. Min Act: -0.1700
Data Index: 3525389 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8056. Min Act: -0.1700
Data Index: 4412199 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8056. Min Act: -0.1700
Data Index: 6458301 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8215. Min Act: -0.1700
Data Index: 5689284 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8056. Min Act: -0.1700
Data Index: 3555927 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8215. Min Act: -0.1700
Data Index: 1250914 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8056. Min Act: -0.1700
Data Index: 77208 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9959. Min Range: -2.9959
Max Act: 2.8056. Min Act: -0.1700
Data Index: 6190301 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19