Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1569 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.7437. Min Act: -0.1700
Data Index: 4107033 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.7437. Min Act: -0.1700
Data Index: 2409393 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.7437. Min Act: -0.1700
Data Index: 2659106 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.7125. Min Act: -0.1700
Data Index: 7283321 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6500. Min Act: -0.1700
Data Index: 2985450 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.6187. Min Act: -0.1700
Data Index: 5101543 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5875. Min Act: -0.1700
Data Index: 896293 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5875. Min Act: -0.1700
Data Index: 8519100 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5875. Min Act: -0.1700
Data Index: 3620237 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5875. Min Act: -0.1700
Data Index: 6175710 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 8024131 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5875. Min Act: -0.1700
Data Index: 4103997 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 423907 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5562. Min Act: -0.1700
Data Index: 2491299 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5250. Min Act: -0.1700
Data Index: 4438382 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4625. Min Act: -0.1700
Data Index: 7089066 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5250. Min Act: -0.1700
Data Index: 1302851 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5250. Min Act: -0.1700
Data Index: 4659491 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.5250. Min Act: -0.1700
Data Index: 522345 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7437. Min Range: -4.7437
Max Act: 4.4937. Min Act: -0.1700
Data Index: 6285654 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19