Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0592. Min Range: -5.0592
Max Act: 5.0592. Min Act: -0.1700
Data Index: 8515090 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.9967. Min Act: -0.1700
Data Index: 7834465 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.8405. Min Act: -0.1700
Data Index: 7504385 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.8405. Min Act: -0.1700
Data Index: 455318 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.8405. Min Act: -0.1700
Data Index: 8597555 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.8405. Min Act: -0.1700
Data Index: 3826113 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.8405. Min Act: -0.1700
Data Index: 2998522 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.7467. Min Act: -0.1700
Data Index: 5914408 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.7780. Min Act: -0.1700
Data Index: 7504384 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.7780. Min Act: -0.1700
Data Index: 1737386 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.7467. Min Act: -0.1700
Data Index: 4794609 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.7467. Min Act: -0.1700
Data Index: 4870808 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.7155. Min Act: -0.1700
Data Index: 7011798 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6842. Min Act: -0.1700
Data Index: 534020 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6842. Min Act: -0.1700
Data Index: 6856026 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6842. Min Act: -0.1700
Data Index: 1544089 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6842. Min Act: -0.1700
Data Index: 4980055 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6217. Min Act: -0.1700
Data Index: 4048233 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6530. Min Act: -0.1700
Data Index: 115323 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0592. Min Range: -5.0592
Max Act: 4.6530. Min Act: -0.1700
Data Index: 696156 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19