Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2462. Min Range: -5.2462
Max Act: 5.2462. Min Act: -0.1700
Data Index: 2259366 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2462. Min Range: -5.2462
Max Act: 5.1212. Min Act: -0.1700
Data Index: 5724729 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2462. Min Range: -5.2462
Max Act: 5.1212. Min Act: -0.1700
Data Index: 5582032 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2462. Min Range: -5.2462
Max Act: 5.0587. Min Act: -0.1700
Data Index: 2318863 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.9962. Min Act: -0.1700
Data Index: 6060909 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.8399. Min Act: -0.1700
Data Index: 5510985 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.8399. Min Act: -0.1700
Data Index: 3420551 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.7774. Min Act: -0.1700
Data Index: 5569796 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.7149. Min Act: -0.1700
Data Index: 7983620 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.7462. Min Act: -0.1700
Data Index: 184030 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.7149. Min Act: -0.1700
Data Index: 5672968 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6524. Min Act: -0.1700
Data Index: 5602928 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.7149. Min Act: -0.1700
Data Index: 3968499 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6837. Min Act: -0.1700
Data Index: 4257089 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6524. Min Act: -0.1700
Data Index: 3034784 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6524. Min Act: -0.1700
Data Index: 5690550 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6524. Min Act: -0.1700
Data Index: 2101130 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6837. Min Act: -0.1700
Data Index: 282485 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6524. Min Act: -0.1700
Data Index: 3082149 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2462. Min Range: -5.2462
Max Act: 4.6524. Min Act: -0.1700
Data Index: 5215539 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19