Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.6583. Min Act: -0.1700
Data Index: 7823070 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.5021. Min Act: -0.1700
Data Index: 6380717 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.4396. Min Act: -0.1700
Data Index: 8253076 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.4083. Min Act: -0.1700
Data Index: 2051036 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.4083. Min Act: -0.1700
Data Index: 7376267 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.4083. Min Act: -0.1700
Data Index: 6745691 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.4083. Min Act: -0.1700
Data Index: 2846869 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.3771. Min Act: -0.1700
Data Index: 4848651 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.3458. Min Act: -0.1700
Data Index: 8632687 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.3146. Min Act: -0.1700
Data Index: 4882008 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.3146. Min Act: -0.1700
Data Index: 961644 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.3146. Min Act: -0.1700
Data Index: 344433 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.2208. Min Act: -0.1700
Data Index: 3258333 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.2521. Min Act: -0.1700
Data Index: 1361462 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.2833. Min Act: -0.1700
Data Index: 6322705 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.2521. Min Act: -0.1700
Data Index: 7520693 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.2208. Min Act: -0.1700
Data Index: 3312060 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.2208. Min Act: -0.1700
Data Index: 6322701 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.2208. Min Act: -0.1700
Data Index: 8759563 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6583. Min Range: -6.6583
Max Act: 6.1583. Min Act: -0.1700
Data Index: 2813912 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19