Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.6583. Min Act: -0.1700
Data Index: 5830575 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.5646. Min Act: -0.1700
Data Index: 509770 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.5021. Min Act: -0.1700
Data Index: 3627508 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.5021. Min Act: -0.1700
Data Index: 1513817 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.3771. Min Act: -0.1700
Data Index: 1701982 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.3458. Min Act: -0.1700
Data Index: 2224762 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.3146. Min Act: -0.1700
Data Index: 217753 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.2521. Min Act: -0.1700
Data Index: 1450604 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.2521. Min Act: -0.1700
Data Index: 8483257 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.2521. Min Act: -0.1700
Data Index: 215474 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.2521. Min Act: -0.1700
Data Index: 2543814 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.2208. Min Act: -0.1700
Data Index: 2172399 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.2208. Min Act: -0.1700
Data Index: 4857875 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.1896. Min Act: -0.1700
Data Index: 4093663 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.1896. Min Act: -0.1700
Data Index: 4958939 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.1583. Min Act: -0.1700
Data Index: 7306298 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.1583. Min Act: -0.1700
Data Index: 850061 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.1271. Min Act: -0.1700
Data Index: 5075827 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.1271. Min Act: -0.1700
Data Index: 2687398 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6583. Min Range: -5.6583
Max Act: 5.1271. Min Act: -0.1700
Data Index: 5385790 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19