Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.3400. Min Act: -0.1700
Data Index: 7453665 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.3712. Min Act: -0.1700
Data Index: 1057678 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.2462. Min Act: -0.1700
Data Index: 8197237 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.2150. Min Act: -0.1700
Data Index: 645889 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.2462. Min Act: -0.1700
Data Index: 283584 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.2150. Min Act: -0.1700
Data Index: 8763813 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1837. Min Act: -0.1700
Data Index: 5889775 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1525. Min Act: -0.1700
Data Index: 4907790 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1837. Min Act: -0.1700
Data Index: 8831307 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1837. Min Act: -0.1700
Data Index: 2493 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1525. Min Act: -0.1700
Data Index: 1186268 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1837. Min Act: -0.1700
Data Index: 1102129 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1837. Min Act: -0.1700
Data Index: 3164531 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1525. Min Act: -0.1700
Data Index: 2144921 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1525. Min Act: -0.1700
Data Index: 1952248 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1212. Min Act: -0.1700
Data Index: 3441606 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.1212. Min Act: -0.1700
Data Index: 5988539 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.0587. Min Act: -0.1700
Data Index: 7704795 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.0587. Min Act: -0.1700
Data Index: 4398427 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3712. Min Range: -5.3712
Max Act: 5.0900. Min Act: -0.1700
Data Index: 2297770 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #19