Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4402 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.5854. Min Act: -0.1700
Data Index: 5203027 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.5229. Min Act: -0.1700
Data Index: 1907020 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.3979. Min Act: -0.1700
Data Index: 1238073 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.3354. Min Act: -0.1700
Data Index: 3734363 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.1479. Min Act: -0.1700
Data Index: 7672752 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.1479. Min Act: -0.1700
Data Index: 2356771 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.0854. Min Act: -0.1700
Data Index: 5356631 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.0854. Min Act: -0.1700
Data Index: 49929 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.0229. Min Act: -0.1700
Data Index: 3036639 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.0229. Min Act: -0.1700
Data Index: 3824986 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.0229. Min Act: -0.1700
Data Index: 165573 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5854. Min Range: -8.5854
Max Act: 8.0229. Min Act: -0.1700
Data Index: 3523920 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.9604. Min Act: -0.1700
Data Index: 7825736 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.8979. Min Act: -0.1700
Data Index: 7620287 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.8979. Min Act: -0.1700
Data Index: 3689126 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.8979. Min Act: -0.1700
Data Index: 4910905 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.8354. Min Act: -0.1700
Data Index: 6947562 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.8354. Min Act: -0.1700
Data Index: 3817393 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.7729. Min Act: -0.1700
Data Index: 6492934 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5854. Min Range: -8.5854
Max Act: 7.7104. Min Act: -0.1700
Data Index: 2992274 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19