Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5831 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.1531. Min Act: -0.1700
Data Index: 8557456 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.1531. Min Act: -0.1700
Data Index: 3389177 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.1219. Min Act: -0.1700
Data Index: 5343369 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.0594. Min Act: -0.1700
Data Index: 7347857 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.0594. Min Act: -0.1700
Data Index: 3161273 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.0281. Min Act: -0.1700
Data Index: 2643814 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9969. Min Act: -0.1700
Data Index: 8511077 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9969. Min Act: -0.1700
Data Index: 7182705 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9656. Min Act: -0.1700
Data Index: 4194360 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9656. Min Act: -0.1700
Data Index: 159165 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9656. Min Act: -0.1700
Data Index: 2544673 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9344. Min Act: -0.1700
Data Index: 4938902 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9344. Min Act: -0.1700
Data Index: 4207436 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9344. Min Act: -0.1700
Data Index: 6045113 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9344. Min Act: -0.1700
Data Index: 5933140 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9031. Min Act: -0.1700
Data Index: 3692060 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9031. Min Act: -0.1700
Data Index: 2830108 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9031. Min Act: -0.1700
Data Index: 7677586 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.8719. Min Act: -0.1700
Data Index: 7287447 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9031. Min Act: -0.1700
Data Index: 5116639 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19