Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 412 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.7650. Min Act: -0.1700
Data Index: 5564142 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.7171. Min Act: -0.1700
Data Index: 4445040 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.6530. Min Act: -0.1700
Data Index: 124521 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.6369. Min Act: -0.1700
Data Index: 790036 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.6369. Min Act: -0.1700
Data Index: 6719217 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5726. Min Act: -0.1700
Data Index: 6769592 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5887. Min Act: -0.1700
Data Index: 8230739 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5726. Min Act: -0.1700
Data Index: 2732459 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5565. Min Act: -0.1700
Data Index: 4859297 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5726. Min Act: -0.1700
Data Index: 875536 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5726. Min Act: -0.1700
Data Index: 1223422 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5565. Min Act: -0.1700
Data Index: 140756 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5726. Min Act: -0.1700
Data Index: 1179742 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5565. Min Act: -0.1700
Data Index: 4899067 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5565. Min Act: -0.1700
Data Index: 7652010 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5403. Min Act: -0.1700
Data Index: 7701178 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5565. Min Act: -0.1700
Data Index: 7851497 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5565. Min Act: -0.1700
Data Index: 3256315 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5726. Min Act: -0.1700
Data Index: 6660627 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7650. Min Range: -2.7650
Max Act: 2.5565. Min Act: -0.1700
Data Index: 6547280 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19