Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2326 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.2705. Min Act: -0.1700
Data Index: 4554629 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.2080. Min Act: -0.1700
Data Index: 1523095 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.2393. Min Act: -0.1700
Data Index: 4755021 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.2080. Min Act: -0.1700
Data Index: 1958084 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1768. Min Act: -0.1700
Data Index: 6514407 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1768. Min Act: -0.1700
Data Index: 8742352 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.2080. Min Act: -0.1700
Data Index: 5242675 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1455. Min Act: -0.1700
Data Index: 3553678 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1455. Min Act: -0.1700
Data Index: 3346892 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1455. Min Act: -0.1700
Data Index: 8420803 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1768. Min Act: -0.1700
Data Index: 8264099 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1455. Min Act: -0.1700
Data Index: 7894939 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1455. Min Act: -0.1700
Data Index: 7513333 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1143. Min Act: -0.1700
Data Index: 4160742 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.0830. Min Act: -0.1700
Data Index: 7863956 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1455. Min Act: -0.1700
Data Index: 4310323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1143. Min Act: -0.1700
Data Index: 2373141 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1455. Min Act: -0.1700
Data Index: 6687146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1143. Min Act: -0.1700
Data Index: 1432288 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2705. Min Range: -5.2705
Max Act: 5.1143. Min Act: -0.1700
Data Index: 2866072 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19