Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.3221. Min Act: -0.1700
Data Index: 5228068 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1971. Min Act: -0.1700
Data Index: 415500 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1971. Min Act: -0.1700
Data Index: 1473973 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1659. Min Act: -0.1700
Data Index: 3703578 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1346. Min Act: -0.1700
Data Index: 2556693 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1034. Min Act: -0.1700
Data Index: 3365685 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1034. Min Act: -0.1700
Data Index: 7662297 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.1034. Min Act: -0.1700
Data Index: 7644313 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0721. Min Act: -0.1700
Data Index: 5942290 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0721. Min Act: -0.1700
Data Index: 690138 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0408. Min Act: -0.1700
Data Index: 6508235 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0096. Min Act: -0.1700
Data Index: 3425110 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0408. Min Act: -0.1700
Data Index: 8529826 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0096. Min Act: -0.1700
Data Index: 2837982 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0096. Min Act: -0.1700
Data Index: 1323347 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0096. Min Act: -0.1700
Data Index: 5942288 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3221. Min Range: -4.3221
Max Act: 3.9783. Min Act: -0.1700
Data Index: 4955337 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3221. Min Range: -4.3221
Max Act: 4.0096. Min Act: -0.1700
Data Index: 7275954 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3221. Min Range: -4.3221
Max Act: 3.9783. Min Act: -0.1700
Data Index: 1350209 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3221. Min Range: -4.3221
Max Act: 3.9783. Min Act: -0.1700
Data Index: 8583513 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19