Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0011. Min Range: -5.0011
Max Act: 5.0011. Min Act: -0.1700
Data Index: 1845472 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0011. Min Range: -5.0011
Max Act: 5.0011. Min Act: -0.1700
Data Index: 6781549 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.8448. Min Act: -0.1700
Data Index: 5179014 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.8448. Min Act: -0.1700
Data Index: 1796600 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.7511. Min Act: -0.1700
Data Index: 7522387 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.6886. Min Act: -0.1700
Data Index: 847332 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.6573. Min Act: -0.1700
Data Index: 8491677 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.6261. Min Act: -0.1700
Data Index: 5571339 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.6261. Min Act: -0.1700
Data Index: 6326595 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.6261. Min Act: -0.1700
Data Index: 7900778 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5948. Min Act: -0.1700
Data Index: 3344595 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5948. Min Act: -0.1700
Data Index: 3345486 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5948. Min Act: -0.1700
Data Index: 811060 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5948. Min Act: -0.1700
Data Index: 3976341 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5636. Min Act: -0.1700
Data Index: 6662078 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5323. Min Act: -0.1700
Data Index: 6902819 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5323. Min Act: -0.1700
Data Index: 2503819 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5323. Min Act: -0.1700
Data Index: 5496264 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5323. Min Act: -0.1700
Data Index: 3396577 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0011. Min Range: -5.0011
Max Act: 4.5011. Min Act: -0.1700
Data Index: 2191781 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19