Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1921 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.2787. Min Act: -0.1700
Data Index: 4918547 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1537. Min Act: -0.1700
Data Index: 4819530 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.1224. Min Act: -0.1700
Data Index: 3535449 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0911. Min Act: -0.1700
Data Index: 7563851 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0911. Min Act: -0.1700
Data Index: 8747556 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0599. Min Act: -0.1700
Data Index: 4136503 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0599. Min Act: -0.1700
Data Index: 7206419 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2787. Min Range: -4.2787
Max Act: 4.0599. Min Act: -0.1700
Data Index: 5669089 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9974. Min Act: -0.1700
Data Index: 5600667 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9036. Min Act: -0.1700
Data Index: 292621 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9348. Min Act: -0.1700
Data Index: 7480372 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9348. Min Act: -0.1700
Data Index: 271521 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9036. Min Act: -0.1700
Data Index: 5954162 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.8723. Min Act: -0.1700
Data Index: 8413921 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9348. Min Act: -0.1700
Data Index: 3089627 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.8723. Min Act: -0.1700
Data Index: 5508425 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.8723. Min Act: -0.1700
Data Index: 8413919 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9036. Min Act: -0.1700
Data Index: 4449600 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.9036. Min Act: -0.1700
Data Index: 7941256 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2787. Min Range: -4.2787
Max Act: 3.8723. Min Act: -0.1700
Data Index: 4030893 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19