Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.6852. Min Act: -0.1700
Data Index: 6446562 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.6227. Min Act: -0.1700
Data Index: 1216433 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4665. Min Act: -0.1700
Data Index: 5105856 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4352. Min Act: -0.1700
Data Index: 7255723 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4352. Min Act: -0.1700
Data Index: 6032993 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4040. Min Act: -0.1700
Data Index: 920711 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4040. Min Act: -0.1699
Data Index: 4654136 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.3727. Min Act: -0.1700
Data Index: 2297885 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4040. Min Act: -0.1700
Data Index: 5432245 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.4040. Min Act: -0.1700
Data Index: 3588733 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.3415. Min Act: -0.1700
Data Index: 5755669 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.3415. Min Act: -0.1700
Data Index: 4023542 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.3415. Min Act: -0.1700
Data Index: 5309555 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.3102. Min Act: -0.1700
Data Index: 3914411 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4644757 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.3102. Min Act: -0.1700
Data Index: 1164514 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.2790. Min Act: -0.1700
Data Index: 3914424 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.2790. Min Act: -0.1700
Data Index: 5755667 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.2790. Min Act: -0.1700
Data Index: 1442141 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6852. Min Range: -5.6852
Max Act: 5.2790. Min Act: -0.1700
Data Index: 7014010 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19