Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1770. Min Range: -6.1770
Max Act: 6.1770. Min Act: -0.1700
Data Index: 426930 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1770. Min Range: -6.1770
Max Act: 6.0520. Min Act: -0.1700
Data Index: 6894186 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.9895. Min Act: -0.1700
Data Index: 4592413 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.9895. Min Act: -0.1700
Data Index: 4354796 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.9270. Min Act: -0.1700
Data Index: 7909687 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8958. Min Act: -0.1700
Data Index: 2830156 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8958. Min Act: -0.1700
Data Index: 3529089 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8958. Min Act: -0.1700
Data Index: 2094154 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8645. Min Act: -0.1700
Data Index: 8005111 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8645. Min Act: -0.1700
Data Index: 6716655 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8645. Min Act: -0.1700
Data Index: 1169169 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8645. Min Act: -0.1700
Data Index: 5159339 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8645. Min Act: -0.1700
Data Index: 5858711 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1193821 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8333. Min Act: -0.1700
Data Index: 2950356 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8333. Min Act: -0.1700
Data Index: 1907530 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8645. Min Act: -0.1700
Data Index: 6174745 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8020. Min Act: -0.1700
Data Index: 5181805 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.8020. Min Act: -0.1700
Data Index: 7551008 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1770. Min Range: -6.1770
Max Act: 5.7708. Min Act: -0.1700
Data Index: 6653557 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19