Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.8441. Min Act: -0.1700
Data Index: 3538343 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.8441. Min Act: -0.1700
Data Index: 1673424 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.8129. Min Act: -0.1700
Data Index: 3377449 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.7816. Min Act: -0.1700
Data Index: 8188696 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.7816. Min Act: -0.1700
Data Index: 2468849 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.7504. Min Act: -0.1700
Data Index: 1541476 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.7191. Min Act: -0.1700
Data Index: 4011855 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.7191. Min Act: -0.1700
Data Index: 2866186 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.7191. Min Act: -0.1700
Data Index: 2121005 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6879. Min Act: -0.1700
Data Index: 2881497 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6879. Min Act: -0.1700
Data Index: 826840 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.7191. Min Act: -0.1700
Data Index: 4768918 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6566. Min Act: -0.1700
Data Index: 5553149 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6566. Min Act: -0.1700
Data Index: 5048940 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6566. Min Act: -0.1700
Data Index: 8709739 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6879. Min Act: -0.1700
Data Index: 3947756 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6566. Min Act: -0.1700
Data Index: 4450566 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6566. Min Act: -0.1700
Data Index: 6677099 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6566. Min Act: -0.1700
Data Index: 6135056 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8441. Min Range: -4.8441
Max Act: 4.6566. Min Act: -0.1700
Data Index: 3197750 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19