Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 794 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.8475. Min Act: -0.1700
Data Index: 8053728 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.6288. Min Act: -0.1700
Data Index: 5312883 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.5975. Min Act: -0.1700
Data Index: 3324510 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.4413. Min Act: -0.1700
Data Index: 1067205 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.4100. Min Act: -0.1700
Data Index: 7163894 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3788. Min Act: -0.1700
Data Index: 6359048 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.4100. Min Act: -0.1700
Data Index: 4612540 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3788. Min Act: -0.1700
Data Index: 5428025 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3475. Min Act: -0.1700
Data Index: 5083242 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3475. Min Act: -0.1700
Data Index: 3034650 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3163. Min Act: -0.1700
Data Index: 4802946 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3163. Min Act: -0.1700
Data Index: 1729588 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3163. Min Act: -0.1700
Data Index: 2281044 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3163. Min Act: -0.1700
Data Index: 889892 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.3163. Min Act: -0.1700
Data Index: 2104052 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.2850. Min Act: -0.1700
Data Index: 933284 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.2850. Min Act: -0.1700
Data Index: 5083243 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.2850. Min Act: -0.1700
Data Index: 2012994 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.2850. Min Act: -0.1700
Data Index: 3862517 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8475. Min Range: -5.8475
Max Act: 5.2850. Min Act: -0.1700
Data Index: 5138256 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19