Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3080 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.1107. Min Range: -1.1107
Max Act: 1.1107. Min Act: -0.1700
Data Index: 6794200 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1107. Min Range: -1.1107
Max Act: 1.0234. Min Act: -0.1700
Data Index: 6543692 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1107. Min Range: -1.1107
Max Act: 1.0147. Min Act: -0.1700
Data Index: 5214870 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9541. Min Act: -0.1700
Data Index: 477049 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9455. Min Act: -0.1699
Data Index: 3741784 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9111. Min Act: -0.1700
Data Index: 38757 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9282. Min Act: -0.1699
Data Index: 1848274 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9368. Min Act: -0.1693
Data Index: 3650772 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9282. Min Act: -0.1699
Data Index: 433493 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9197. Min Act: -0.1699
Data Index: 6189727 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9197. Min Act: -0.1700
Data Index: 8671877 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9282. Min Act: -0.1699
Data Index: 3619278 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9111. Min Act: -0.1700
Data Index: 1280160 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.9025. Min Act: -0.1700
Data Index: 1571775 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.8940. Min Act: -0.1700
Data Index: 1614457 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.8940. Min Act: -0.1700
Data Index: 6249323 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.8684. Min Act: -0.1698
Data Index: 8366373 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.8684. Min Act: -0.1685
Data Index: 1366840 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.8684. Min Act: -0.1700
Data Index: 6464553 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1107. Min Range: -1.1107
Max Act: 0.8429. Min Act: -0.1698
Data Index: 6422506 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19