Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1685 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.9844. Min Act: -0.1700
Data Index: 4286149 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.8906. Min Act: -0.1700
Data Index: 1245754 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.8594. Min Act: -0.1700
Data Index: 5246388 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.7656. Min Act: -0.1700
Data Index: 6061018 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.7344. Min Act: -0.1700
Data Index: 2316393 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6719. Min Act: -0.1700
Data Index: 8821384 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.7031. Min Act: -0.1700
Data Index: 6840648 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6719. Min Act: -0.1700
Data Index: 8789741 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6719. Min Act: -0.1700
Data Index: 4890386 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6406. Min Act: -0.1700
Data Index: 4934530 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6719. Min Act: -0.1700
Data Index: 726664 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6719. Min Act: -0.1700
Data Index: 7440807 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6406. Min Act: -0.1700
Data Index: 8468177 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6406. Min Act: -0.1700
Data Index: 1317606 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6406. Min Act: -0.1700
Data Index: 2997363 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.5781. Min Act: -0.1700
Data Index: 669744 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.5781. Min Act: -0.1700
Data Index: 6745687 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.6094. Min Act: -0.1700
Data Index: 4871866 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.5469. Min Act: -0.1700
Data Index: 3551 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9844. Min Range: -4.9844
Max Act: 4.5781. Min Act: -0.1700
Data Index: 8324588 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19