Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.7209. Min Act: -0.1700
Data Index: 3320470 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.4396. Min Act: -0.1700
Data Index: 886176 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.4396. Min Act: -0.1700
Data Index: 1418197 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.3771. Min Act: -0.1700
Data Index: 7846475 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.2834. Min Act: -0.1700
Data Index: 2713749 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.2521. Min Act: -0.1700
Data Index: 886172 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.1896. Min Act: -0.1700
Data Index: 886174 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.1271. Min Act: -0.1700
Data Index: 1275199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.0959. Min Act: -0.1700
Data Index: 1117548 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.0959. Min Act: -0.1700
Data Index: 1287821 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.0334. Min Act: -0.1700
Data Index: 5439136 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.0021. Min Act: -0.1700
Data Index: 886175 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7209. Min Range: -5.7209
Max Act: 5.0021. Min Act: -0.1700
Data Index: 6914 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7209. Min Range: -5.7209
Max Act: 4.9709. Min Act: -0.1700
Data Index: 6793290 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7209. Min Range: -5.7209
Max Act: 4.9709. Min Act: -0.1700
Data Index: 8714002 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7209. Min Range: -5.7209
Max Act: 4.9709. Min Act: -0.1700
Data Index: 3813169 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7209. Min Range: -5.7209
Max Act: 4.9396. Min Act: -0.1700
Data Index: 101058 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7209. Min Range: -5.7209
Max Act: 4.9396. Min Act: -0.1700
Data Index: 7938957 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7209. Min Range: -5.7209
Max Act: 4.9084. Min Act: -0.1700
Data Index: 1066416 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7209. Min Range: -5.7209
Max Act: 4.9396. Min Act: -0.1700
Data Index: 5833310 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19