Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 449 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1583. Min Range: -7.1583
Max Act: 7.1270. Min Act: -0.1700
Data Index: 1346940 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1583. Min Range: -7.1583
Max Act: 7.1583. Min Act: -0.1700
Data Index: 8294689 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1583. Min Range: -7.1583
Max Act: 7.0333. Min Act: -0.1700
Data Index: 7924841 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.9708. Min Act: -0.1700
Data Index: 7276440 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.9083. Min Act: -0.1700
Data Index: 5842700 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.8458. Min Act: -0.1700
Data Index: 3274288 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.8770. Min Act: -0.1700
Data Index: 1484248 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.8145. Min Act: -0.1700
Data Index: 7503343 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.8145. Min Act: -0.1700
Data Index: 7153656 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7833. Min Act: -0.1700
Data Index: 3690410 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7833. Min Act: -0.1700
Data Index: 222156 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7833. Min Act: -0.1700
Data Index: 2234709 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7520. Min Act: -0.1700
Data Index: 6402383 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7520. Min Act: -0.1700
Data Index: 6698543 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7520. Min Act: -0.1700
Data Index: 6787106 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7520. Min Act: -0.1700
Data Index: 4474154 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7208. Min Act: -0.1700
Data Index: 5713893 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7208. Min Act: -0.1700
Data Index: 779089 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7208. Min Act: -0.1700
Data Index: 801077 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1583. Min Range: -7.1583
Max Act: 6.7208. Min Act: -0.1700
Data Index: 3234051 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19