Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0879. Min Range: -6.0879
Max Act: 6.0879. Min Act: -0.1700
Data Index: 4458753 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0879. Min Range: -6.0879
Max Act: 6.0879. Min Act: -0.1700
Data Index: 5276595 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.8692. Min Act: -0.1700
Data Index: 6519877 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.7754. Min Act: -0.1700
Data Index: 3296976 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.8379. Min Act: -0.1700
Data Index: 6427880 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.7442. Min Act: -0.1700
Data Index: 7021574 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.7129. Min Act: -0.1700
Data Index: 2118546 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.6817. Min Act: -0.1700
Data Index: 5865632 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.6192. Min Act: -0.1700
Data Index: 5166400 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.8067. Min Act: -0.1700
Data Index: 6462623 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.6192. Min Act: -0.1700
Data Index: 3978861 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.6504. Min Act: -0.1700
Data Index: 6598809 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.6504. Min Act: -0.1700
Data Index: 4357849 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.5879. Min Act: -0.1700
Data Index: 4213851 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.5254. Min Act: -0.1700
Data Index: 6236289 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.5879. Min Act: -0.1700
Data Index: 4442202 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.5879. Min Act: -0.1700
Data Index: 6972766 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.5879. Min Act: -0.1700
Data Index: 849376 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.5254. Min Act: -0.1700
Data Index: 2490742 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0879. Min Range: -6.0879
Max Act: 5.5567. Min Act: -0.1700
Data Index: 4192802 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19