Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.4660. Min Act: -0.1700
Data Index: 1608216 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.3410. Min Act: -0.1700
Data Index: 8005325 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.3097. Min Act: -0.1700
Data Index: 630758 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.3097. Min Act: -0.1700
Data Index: 810005 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2785. Min Act: -0.1700
Data Index: 1052313 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2472. Min Act: -0.1700
Data Index: 4612265 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2472. Min Act: -0.1700
Data Index: 7043751 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2472. Min Act: -0.1700
Data Index: 7524622 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2472. Min Act: -0.1700
Data Index: 1328802 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2472. Min Act: -0.1700
Data Index: 8548600 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2472. Min Act: -0.1700
Data Index: 3079976 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2472. Min Act: -0.1700
Data Index: 1395330 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1700
Data Index: 2971973 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1699
Data Index: 2806794 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1700
Data Index: 2116751 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1700
Data Index: 5270542 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1700
Data Index: 5210561 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1700
Data Index: 35842 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1700
Data Index: 5064260 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4660. Min Range: -5.4660
Max Act: 5.2160. Min Act: -0.1700
Data Index: 149619 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19