Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 931 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3313. Min Range: -7.3313
Max Act: 7.3313. Min Act: -0.1700
Data Index: 6367620 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3313. Min Range: -7.3313
Max Act: 7.0813. Min Act: -0.1700
Data Index: 201117 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.9876. Min Act: -0.1700
Data Index: 2209280 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3313. Min Range: -7.3313
Max Act: 7.0188. Min Act: -0.1700
Data Index: 2972917 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.9876. Min Act: -0.1700
Data Index: 6409543 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8626. Min Act: -0.1700
Data Index: 6724835 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8626. Min Act: -0.1700
Data Index: 4643620 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8938. Min Act: -0.1700
Data Index: 2074946 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8313. Min Act: -0.1700
Data Index: 4020133 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8313. Min Act: -0.1700
Data Index: 7531078 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.7688. Min Act: -0.1700
Data Index: 909991 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8001. Min Act: -0.1700
Data Index: 7992802 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.7688. Min Act: -0.1700
Data Index: 4316847 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.8001. Min Act: -0.1700
Data Index: 3727930 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.6751. Min Act: -0.1700
Data Index: 2641534 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.7063. Min Act: -0.1700
Data Index: 6822058 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.7063. Min Act: -0.1700
Data Index: 8232468 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.6751. Min Act: -0.1700
Data Index: 6856771 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.6751. Min Act: -0.1700
Data Index: 232011 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3313. Min Range: -7.3313
Max Act: 6.6751. Min Act: -0.1700
Data Index: 8512668 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19