Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3709 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.9570. Min Act: -0.1700
Data Index: 6520831 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.8632. Min Act: -0.1700
Data Index: 3366392 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.8632. Min Act: -0.1700
Data Index: 5425405 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.8320. Min Act: -0.1700
Data Index: 4251842 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.8007. Min Act: -0.1700
Data Index: 5208388 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.7382. Min Act: -0.1700
Data Index: 6303902 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.7382. Min Act: -0.1700
Data Index: 2868882 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.7382. Min Act: -0.1700
Data Index: 2520879 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6757. Min Act: -0.1700
Data Index: 1361763 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6445. Min Act: -0.1700
Data Index: 4282223 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.6132. Min Act: -0.1700
Data Index: 8434572 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5507. Min Act: -0.1700
Data Index: 833033 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5820. Min Act: -0.1700
Data Index: 3187484 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5507. Min Act: -0.1700
Data Index: 8140665 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5195. Min Act: -0.1700
Data Index: 2866531 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5195. Min Act: -0.1700
Data Index: 7527298 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5507. Min Act: -0.1700
Data Index: 2368691 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.5195. Min Act: -0.1700
Data Index: 1358688 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.4882. Min Act: -0.1700
Data Index: 4688631 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9570. Min Range: -5.9570
Max Act: 5.4882. Min Act: -0.1700
Data Index: 7006089 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19