Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.7543. Min Act: -0.1700
Data Index: 565496 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.7543. Min Act: -0.1700
Data Index: 5682051 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.6918. Min Act: -0.1700
Data Index: 941452 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.6605. Min Act: -0.1700
Data Index: 3457504 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.6605. Min Act: -0.1700
Data Index: 7711250 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.6605. Min Act: -0.1700
Data Index: 7070064 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.5668. Min Act: -0.1700
Data Index: 7708748 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.5668. Min Act: -0.1700
Data Index: 7863361 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.5043. Min Act: -0.1700
Data Index: 276593 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.5043. Min Act: -0.1700
Data Index: 101401 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.5355. Min Act: -0.1700
Data Index: 1391290 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.5355. Min Act: -0.1700
Data Index: 7447654 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.4730. Min Act: -0.1700
Data Index: 6762641 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.5043. Min Act: -0.1700
Data Index: 7770731 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.4730. Min Act: -0.1700
Data Index: 2675174 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.4730. Min Act: -0.1700
Data Index: 4056531 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.4730. Min Act: -0.1700
Data Index: 753184 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.4730. Min Act: -0.1700
Data Index: 6523511 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.4418. Min Act: -0.1700
Data Index: 7216942 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7543. Min Range: -4.7543
Max Act: 4.4418. Min Act: -0.1700
Data Index: 2005091 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19