Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3350 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.4023. Min Act: -0.1700
Data Index: 7265996 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.2773. Min Act: -0.1700
Data Index: 5941048 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.2148. Min Act: -0.1700
Data Index: 1921397 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.1523. Min Act: -0.1700
Data Index: 4610488 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.1523. Min Act: -0.1700
Data Index: 4181157 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.1523. Min Act: -0.1700
Data Index: 5347522 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.0898. Min Act: -0.1700
Data Index: 2993458 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.0586. Min Act: -0.1700
Data Index: 4361200 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4023. Min Range: -5.4023
Max Act: 5.0273. Min Act: -0.1700
Data Index: 1698707 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9961. Min Act: -0.1700
Data Index: 677855 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9648. Min Act: -0.1700
Data Index: 3807653 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9648. Min Act: -0.1700
Data Index: 4996487 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9648. Min Act: -0.1700
Data Index: 1706224 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9336. Min Act: -0.1700
Data Index: 4197199 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9023. Min Act: -0.1700
Data Index: 2732738 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.8711. Min Act: -0.1700
Data Index: 7591622 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.9336. Min Act: -0.1700
Data Index: 6440859 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.8711. Min Act: -0.1700
Data Index: 2458598 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.8398. Min Act: -0.1700
Data Index: 4317033 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4023. Min Range: -5.4023
Max Act: 4.8086. Min Act: -0.1700
Data Index: 1629131 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19