Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4028 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.5112. Min Act: -0.1699
Data Index: 7896528 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4799. Min Act: -0.1700
Data Index: 7712240 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.4174. Min Act: -0.1700
Data Index: 4354629 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3862. Min Act: -0.1700
Data Index: 6541651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3549. Min Act: -0.1700
Data Index: 1076538 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3549. Min Act: -0.1700
Data Index: 8236013 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3549. Min Act: -0.1700
Data Index: 6851624 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3549. Min Act: -0.1700
Data Index: 5353896 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3549. Min Act: -0.1700
Data Index: 7219921 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3237. Min Act: -0.1700
Data Index: 7863546 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3237. Min Act: -0.1700
Data Index: 518970 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3549. Min Act: -0.1700
Data Index: 4084330 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.3237. Min Act: -0.1700
Data Index: 8730894 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.2924. Min Act: -0.1700
Data Index: 6639025 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.2924. Min Act: -0.1700
Data Index: 18256 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.2924. Min Act: -0.1700
Data Index: 2214867 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.2924. Min Act: -0.1700
Data Index: 4528556 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.2924. Min Act: -0.1700
Data Index: 4588459 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.2924. Min Act: -0.1700
Data Index: 7390623 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5112. Min Range: -4.5112
Max Act: 4.2924. Min Act: -0.1700
Data Index: 3565900 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19