Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1323. Min Range: -6.1323
Max Act: 6.1323. Min Act: -0.1700
Data Index: 4963618 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6948. Min Act: -0.1700
Data Index: 7708748 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6635. Min Act: -0.1700
Data Index: 379359 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6323. Min Act: -0.1700
Data Index: 4734713 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6323. Min Act: -0.1700
Data Index: 7942780 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6323. Min Act: -0.1700
Data Index: 5792388 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.6010. Min Act: -0.1700
Data Index: 7066670 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5698. Min Act: -0.1700
Data Index: 4436573 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5385. Min Act: -0.1700
Data Index: 8233749 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5385. Min Act: -0.1700
Data Index: 7924192 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5073. Min Act: -0.1700
Data Index: 1361935 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5073. Min Act: -0.1700
Data Index: 2666827 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5073. Min Act: -0.1700
Data Index: 7970454 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4760. Min Act: -0.1700
Data Index: 4346671 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.5073. Min Act: -0.1700
Data Index: 7236185 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4760. Min Act: -0.1700
Data Index: 7707591 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4448. Min Act: -0.1700
Data Index: 956892 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4448. Min Act: -0.1700
Data Index: 5747409 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4448. Min Act: -0.1700
Data Index: 267646 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1323. Min Range: -6.1323
Max Act: 5.4760. Min Act: -0.1700
Data Index: 3260141 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19