Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.9531. Min Act: -0.1700
Data Index: 1014282 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.9531. Min Act: -0.1700
Data Index: 3165627 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.7656. Min Act: -0.1700
Data Index: 3872327 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.7656. Min Act: -0.1700
Data Index: 3315594 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.7031. Min Act: -0.1700
Data Index: 4833575 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.7031. Min Act: -0.1700
Data Index: 5510125 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.7031. Min Act: -0.1700
Data Index: 3283696 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.5781. Min Act: -0.1700
Data Index: 4284451 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.6406. Min Act: -0.1700
Data Index: 480002 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.5781. Min Act: -0.1700
Data Index: 4179784 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.5156. Min Act: -0.1700
Data Index: 905201 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.5156. Min Act: -0.1700
Data Index: 7344070 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.5156. Min Act: -0.1700
Data Index: 1738910 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.3906. Min Act: -0.1700
Data Index: 2305292 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.5156. Min Act: -0.1700
Data Index: 1593025 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.4531. Min Act: -0.1700
Data Index: 6012640 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.4531. Min Act: -0.1700
Data Index: 2731932 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.4531. Min Act: -0.1700
Data Index: 7152358 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.4531. Min Act: -0.1700
Data Index: 8670447 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9531. Min Range: -8.9531
Max Act: 8.4531. Min Act: -0.1700
Data Index: 6351904 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19