Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 155 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4577. Min Range: -4.4577
Max Act: 4.4577. Min Act: -0.1700
Data Index: 866101 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4577. Min Range: -4.4577
Max Act: 4.2389. Min Act: -0.1700
Data Index: 3185045 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4577. Min Range: -4.4577
Max Act: 4.1452. Min Act: -0.1700
Data Index: 5485238 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.9889. Min Act: -0.1700
Data Index: 3675522 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.9889. Min Act: -0.1700
Data Index: 3106646 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.9576. Min Act: -0.1700
Data Index: 8516128 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.9264. Min Act: -0.1700
Data Index: 6121877 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.9576. Min Act: -0.1700
Data Index: 1918471 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.9264. Min Act: -0.1700
Data Index: 1638464 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8951. Min Act: -0.1700
Data Index: 4948825 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8951. Min Act: -0.1700
Data Index: 7717920 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8951. Min Act: -0.1700
Data Index: 5093833 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8951. Min Act: -0.1700
Data Index: 3282853 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8638. Min Act: -0.1700
Data Index: 4469607 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8638. Min Act: -0.1700
Data Index: 1734510 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8638. Min Act: -0.1700
Data Index: 162610 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8638. Min Act: -0.1700
Data Index: 1686102 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8951. Min Act: -0.1700
Data Index: 2309452 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 1193976 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4577. Min Range: -4.4577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 5027997 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19