Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2067. Min Range: -6.2067
Max Act: 6.2067. Min Act: -0.1700
Data Index: 7607433 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6195735 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.6754. Min Act: -0.1700
Data Index: 3021620 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.6442. Min Act: -0.1700
Data Index: 4798559 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.5817. Min Act: -0.1700
Data Index: 7004354 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.5504. Min Act: -0.1700
Data Index: 8354926 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1396123 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.5192. Min Act: -0.1700
Data Index: 1641398 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4879. Min Act: -0.1700
Data Index: 7147535 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.5192. Min Act: -0.1700
Data Index: 2808918 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4879. Min Act: -0.1700
Data Index: 6301403 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4879. Min Act: -0.1700
Data Index: 4621089 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4879. Min Act: -0.1700
Data Index: 5014939 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4567. Min Act: -0.1700
Data Index: 6403482 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4567. Min Act: -0.1700
Data Index: 6485788 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4567. Min Act: -0.1700
Data Index: 5291203 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4254. Min Act: -0.1700
Data Index: 7421022 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4254. Min Act: -0.1700
Data Index: 2109709 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4254. Min Act: -0.1700
Data Index: 1319630 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2067. Min Range: -6.2067
Max Act: 5.4254. Min Act: -0.1700
Data Index: 2232058 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19