Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4087 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.8276. Min Act: -0.1700
Data Index: 8423520 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.8276. Min Act: -0.1700
Data Index: 6289544 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.7651. Min Act: -0.1700
Data Index: 4276816 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.7339. Min Act: -0.1700
Data Index: 2323299 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.7026. Min Act: -0.1700
Data Index: 245291 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.7026. Min Act: -0.1700
Data Index: 722595 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5776. Min Act: -0.1700
Data Index: 6800986 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.6401. Min Act: -0.1700
Data Index: 424276 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5776. Min Act: -0.1700
Data Index: 755678 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5776. Min Act: -0.1700
Data Index: 4284694 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5776. Min Act: -0.1700
Data Index: 3576718 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5151. Min Act: -0.1700
Data Index: 7118118 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5464. Min Act: -0.1700
Data Index: 7656865 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5464. Min Act: -0.1700
Data Index: 4578748 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5464. Min Act: -0.1700
Data Index: 765652 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.5151. Min Act: -0.1700
Data Index: 3274623 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.4839. Min Act: -0.1700
Data Index: 3825331 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.4839. Min Act: -0.1700
Data Index: 955171 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.4839. Min Act: -0.1700
Data Index: 5634301 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8276. Min Range: -4.8276
Max Act: 4.4839. Min Act: -0.1700
Data Index: 3825334 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19