Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1849 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.3793. Min Act: -0.1700
Data Index: 7417147 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.1918. Min Act: -0.1700
Data Index: 5587561 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.1918. Min Act: -0.1700
Data Index: 3227403 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.1293. Min Act: -0.1700
Data Index: 2938796 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.1918. Min Act: -0.1700
Data Index: 1570547 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0668. Min Act: -0.1700
Data Index: 2154358 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0668. Min Act: -0.1700
Data Index: 504989 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0355. Min Act: -0.1700
Data Index: 7794822 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0355. Min Act: -0.1700
Data Index: 8690871 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0355. Min Act: -0.1700
Data Index: 1685559 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9730. Min Act: -0.1700
Data Index: 6090551 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3793. Min Range: -6.3793
Max Act: 6.0043. Min Act: -0.1700
Data Index: 3799820 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9418. Min Act: -0.1700
Data Index: 3886257 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9418. Min Act: -0.1700
Data Index: 1573524 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9105. Min Act: -0.1700
Data Index: 7742430 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9105. Min Act: -0.1700
Data Index: 8712973 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9105. Min Act: -0.1700
Data Index: 3206687 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9105. Min Act: -0.1700
Data Index: 3080715 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.8480. Min Act: -0.1700
Data Index: 606177 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3793. Min Range: -6.3793
Max Act: 5.9105. Min Act: -0.1700
Data Index: 602275 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19