Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.5493. Min Act: -0.1700
Data Index: 705963 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.3931. Min Act: -0.1700
Data Index: 2905395 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.2993. Min Act: -0.1700
Data Index: 3514276 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.2368. Min Act: -0.1700
Data Index: 2972648 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.2368. Min Act: -0.1700
Data Index: 7555690 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1743. Min Act: -0.1700
Data Index: 5553749 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1743. Min Act: -0.1700
Data Index: 8649896 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1431. Min Act: -0.1700
Data Index: 4066569 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 3021657 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 7890976 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 1255138 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 4141717 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 2447365 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 7497319 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 8368724 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.0806. Min Act: -0.1700
Data Index: 5564164 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.0806. Min Act: -0.1700
Data Index: 3196354 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.1118. Min Act: -0.1700
Data Index: 1383199 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.0493. Min Act: -0.1700
Data Index: 2743431 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5493. Min Range: -5.5493
Max Act: 5.0493. Min Act: -0.1700
Data Index: 7553138 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19