Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.9300. Min Act: -0.1700
Data Index: 356319 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.8675. Min Act: -0.1700
Data Index: 4683566 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.8050. Min Act: -0.1700
Data Index: 3776479 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.8050. Min Act: -0.1700
Data Index: 530612 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.7738. Min Act: -0.1700
Data Index: 163464 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.6175. Min Act: -0.1700
Data Index: 3637802 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.7425. Min Act: -0.1700
Data Index: 3610482 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.7425. Min Act: -0.1700
Data Index: 1062256 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.7425. Min Act: -0.1700
Data Index: 1856982 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.7425. Min Act: -0.1700
Data Index: 8744269 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.6488. Min Act: -0.1700
Data Index: 7563399 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.6175. Min Act: -0.1700
Data Index: 4110299 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.6800. Min Act: -0.1700
Data Index: 4871129 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.6488. Min Act: -0.1700
Data Index: 377598 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.5863. Min Act: -0.1700
Data Index: 1398870 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.5863. Min Act: -0.1700
Data Index: 150203 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.5550. Min Act: -0.1700
Data Index: 6553788 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.6175. Min Act: -0.1700
Data Index: 7913673 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.5863. Min Act: -0.1700
Data Index: 8528440 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9300. Min Range: -4.9300
Max Act: 4.5863. Min Act: -0.1700
Data Index: 6908500 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19