Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5562 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.3321. Min Act: -0.1700
Data Index: 2794862 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.3321. Min Act: -0.1700
Data Index: 7006445 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.3321. Min Act: -0.1700
Data Index: 7925097 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.2696. Min Act: -0.1700
Data Index: 6037478 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.1446. Min Act: -0.1700
Data Index: 5844353 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.0821. Min Act: -0.1700
Data Index: 2414547 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.0508. Min Act: -0.1700
Data Index: 3691376 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.0508. Min Act: -0.1700
Data Index: 1302196 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.0508. Min Act: -0.1700
Data Index: 3948937 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3321. Min Range: -6.3321
Max Act: 6.0508. Min Act: -0.1700
Data Index: 6004627 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.9883. Min Act: -0.1700
Data Index: 7129813 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.9883. Min Act: -0.1700
Data Index: 6206497 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.9883. Min Act: -0.1700
Data Index: 666680 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.9571. Min Act: -0.1700
Data Index: 6424320 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.9258. Min Act: -0.1700
Data Index: 1300613 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.8946. Min Act: -0.1700
Data Index: 8406580 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.8946. Min Act: -0.1700
Data Index: 4558082 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.9258. Min Act: -0.1700
Data Index: 274683 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.9258. Min Act: -0.1700
Data Index: 2465153 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3321. Min Range: -6.3321
Max Act: 5.8946. Min Act: -0.1700
Data Index: 1434932 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19