Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1509 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.9915. Min Act: -0.1700
Data Index: 5522121 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.9603. Min Act: -0.1700
Data Index: 2028935 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.8665. Min Act: -0.1700
Data Index: 5544843 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.8353. Min Act: -0.1700
Data Index: 5722379 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.8353. Min Act: -0.1700
Data Index: 3215444 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.8353. Min Act: -0.1700
Data Index: 727593 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.8040. Min Act: -0.1700
Data Index: 4533599 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.8353. Min Act: -0.1700
Data Index: 5422191 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7728. Min Act: -0.1700
Data Index: 5900125 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7728. Min Act: -0.1700
Data Index: 571877 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7415. Min Act: -0.1700
Data Index: 3497753 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7415. Min Act: -0.1700
Data Index: 482172 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7103. Min Act: -0.1700
Data Index: 7677007 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7415. Min Act: -0.1700
Data Index: 5009785 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7103. Min Act: -0.1700
Data Index: 3421706 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7415. Min Act: -0.1700
Data Index: 4466755 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7415. Min Act: -0.1700
Data Index: 377197 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7103. Min Act: -0.1700
Data Index: 853810 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7103. Min Act: -0.1700
Data Index: 5191761 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9915. Min Range: -5.9915
Max Act: 5.7415. Min Act: -0.1700
Data Index: 5167853 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19