Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.4712. Min Act: -0.1700
Data Index: 8572191 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 6971459 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.2212. Min Act: -0.1700
Data Index: 2766941 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.1275. Min Act: -0.1700
Data Index: 2282272 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0962. Min Act: -0.1700
Data Index: 3345781 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0962. Min Act: -0.1700
Data Index: 5608967 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0650. Min Act: -0.1700
Data Index: 5721112 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0650. Min Act: -0.1700
Data Index: 3863194 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0650. Min Act: -0.1700
Data Index: 2256953 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0337. Min Act: -0.1700
Data Index: 1639415 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0025. Min Act: -0.1700
Data Index: 5573518 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0337. Min Act: -0.1700
Data Index: 8631542 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0025. Min Act: -0.1700
Data Index: 5201529 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4712. Min Range: -6.4712
Max Act: 6.0025. Min Act: -0.1700
Data Index: 4005309 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4712. Min Range: -6.4712
Max Act: 5.9712. Min Act: -0.1700
Data Index: 8103700 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4712. Min Range: -6.4712
Max Act: 5.9712. Min Act: -0.1700
Data Index: 5982277 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4712. Min Range: -6.4712
Max Act: 5.9712. Min Act: -0.1700
Data Index: 4172059 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4712. Min Range: -6.4712
Max Act: 5.9400. Min Act: -0.1700
Data Index: 5977642 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4712. Min Range: -6.4712
Max Act: 5.9400. Min Act: -0.1700
Data Index: 6786360 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4712. Min Range: -6.4712
Max Act: 5.9400. Min Act: -0.1700
Data Index: 6919153 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19