Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.5639. Min Act: -0.1700
Data Index: 3228356 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.4389. Min Act: -0.1700
Data Index: 1221259 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.4076. Min Act: -0.1700
Data Index: 3196532 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.3764. Min Act: -0.1700
Data Index: 8259494 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.4389. Min Act: -0.1700
Data Index: 3937878 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.4076. Min Act: -0.1700
Data Index: 5150087 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.3764. Min Act: -0.1700
Data Index: 1726658 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.3451. Min Act: -0.1700
Data Index: 1369468 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.3139. Min Act: -0.1700
Data Index: 53796 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.3139. Min Act: -0.1700
Data Index: 4314081 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.3139. Min Act: -0.1700
Data Index: 6986977 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2826. Min Act: -0.1700
Data Index: 6338549 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2826. Min Act: -0.1700
Data Index: 2026751 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2514. Min Act: -0.1700
Data Index: 8492754 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2514. Min Act: -0.1700
Data Index: 7735608 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2201. Min Act: -0.1700
Data Index: 78006 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2514. Min Act: -0.1700
Data Index: 2770505 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2201. Min Act: -0.1700
Data Index: 8116879 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2201. Min Act: -0.1700
Data Index: 7472781 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5639. Min Range: -5.5639
Max Act: 5.2201. Min Act: -0.1700
Data Index: 6710785 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19