Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.1282. Min Act: -0.1700
Data Index: 5865917 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.1124. Min Act: -0.1700
Data Index: 4713168 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.0967. Min Act: -0.1700
Data Index: 5569279 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.0809. Min Act: -0.1700
Data Index: 4437760 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.0493. Min Act: -0.1700
Data Index: 5020356 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.0336. Min Act: -0.1700
Data Index: 8224642 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.0020. Min Act: -0.1700
Data Index: 5815142 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1282. Min Range: -3.1282
Max Act: 3.0178. Min Act: -0.1700
Data Index: 4862042 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.9703. Min Act: -0.1700
Data Index: 1606875 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.9545. Min Act: -0.1700
Data Index: 4511784 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.9387. Min Act: -0.1700
Data Index: 4486527 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.9229. Min Act: -0.1700
Data Index: 6258276 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.9070. Min Act: -0.1700
Data Index: 4683534 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.9229. Min Act: -0.1700
Data Index: 4019829 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.9229. Min Act: -0.1700
Data Index: 6624716 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.8753. Min Act: -0.1700
Data Index: 5010751 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.8753. Min Act: -0.1700
Data Index: 2979600 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.8753. Min Act: -0.1700
Data Index: 1231366 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.8753. Min Act: -0.1700
Data Index: 7257485 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1282. Min Range: -3.1282
Max Act: 2.8435. Min Act: -0.1700
Data Index: 6619693 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19