Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.7653. Min Act: -0.1700
Data Index: 522197 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.4528. Min Act: -0.1700
Data Index: 2710612 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.3278. Min Act: -0.1700
Data Index: 1005049 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.3278. Min Act: -0.1700
Data Index: 3662739 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.2653. Min Act: -0.1700
Data Index: 2617138 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.2653. Min Act: -0.1700
Data Index: 413115 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.2340. Min Act: -0.1700
Data Index: 3338454 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.2028. Min Act: -0.1700
Data Index: 1733488 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.1715. Min Act: -0.1700
Data Index: 3315918 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.1403. Min Act: -0.1700
Data Index: 6136146 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.1403. Min Act: -0.1700
Data Index: 7117580 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.1090. Min Act: -0.1700
Data Index: 5757435 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.1090. Min Act: -0.1700
Data Index: 490930 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.1090. Min Act: -0.1700
Data Index: 4348027 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.0778. Min Act: -0.1700
Data Index: 1702997 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.0465. Min Act: -0.1700
Data Index: 6778539 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.0778. Min Act: -0.1700
Data Index: 6495284 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.0778. Min Act: -0.1700
Data Index: 1273796 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.1090. Min Act: -0.1700
Data Index: 673108 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7653. Min Range: -6.7653
Max Act: 6.0778. Min Act: -0.1700
Data Index: 1921869 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19