Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0912. Min Range: -6.0912
Max Act: 6.0912. Min Act: -0.1700
Data Index: 2865933 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.6850. Min Act: -0.1700
Data Index: 1306810 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.6850. Min Act: -0.1700
Data Index: 2822995 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.6225. Min Act: -0.1700
Data Index: 5481961 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.6225. Min Act: -0.1700
Data Index: 2413297 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.6537. Min Act: -0.1700
Data Index: 1306808 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.5912. Min Act: -0.1700
Data Index: 1306806 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.5600. Min Act: -0.1700
Data Index: 6632880 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.5600. Min Act: -0.1700
Data Index: 1306812 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4975. Min Act: -0.1700
Data Index: 255921 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4975. Min Act: -0.1700
Data Index: 6892812 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4350. Min Act: -0.1700
Data Index: 8699339 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4662. Min Act: -0.1700
Data Index: 74247 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4037. Min Act: -0.1700
Data Index: 5975418 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4350. Min Act: -0.1700
Data Index: 908330 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4037. Min Act: -0.1700
Data Index: 483921 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4037. Min Act: -0.1700
Data Index: 6354504 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4037. Min Act: -0.1700
Data Index: 1778414 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4037. Min Act: -0.1700
Data Index: 1363166 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0912. Min Range: -6.0912
Max Act: 5.4037. Min Act: -0.1700
Data Index: 361319 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19