Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3499. Min Range: -6.3499
Max Act: 6.3499. Min Act: -0.1700
Data Index: 1662293 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3499. Min Range: -6.3499
Max Act: 6.2249. Min Act: -0.1700
Data Index: 6756765 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3499. Min Range: -6.3499
Max Act: 6.1936. Min Act: -0.1700
Data Index: 5156599 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3499. Min Range: -6.3499
Max Act: 6.0999. Min Act: -0.1700
Data Index: 1302578 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.9749. Min Act: -0.1700
Data Index: 909267 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.9436. Min Act: -0.1700
Data Index: 6711918 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.9124. Min Act: -0.1700
Data Index: 7691648 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8811. Min Act: -0.1700
Data Index: 4675030 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8811. Min Act: -0.1700
Data Index: 1030986 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8186. Min Act: -0.1700
Data Index: 6936412 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8499. Min Act: -0.1700
Data Index: 809354 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8499. Min Act: -0.1700
Data Index: 1923191 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8499. Min Act: -0.1700
Data Index: 1330084 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8186. Min Act: -0.1700
Data Index: 283728 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8186. Min Act: -0.1700
Data Index: 8324075 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.8186. Min Act: -0.1700
Data Index: 8448731 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.7874. Min Act: -0.1700
Data Index: 6360780 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.7874. Min Act: -0.1700
Data Index: 7458320 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.7874. Min Act: -0.1700
Data Index: 4344714 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3499. Min Range: -6.3499
Max Act: 5.7874. Min Act: -0.1700
Data Index: 8355052 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19