Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3204. Min Range: -7.3204
Max Act: 7.3204. Min Act: -0.1700
Data Index: 750350 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.8204. Min Act: -0.1700
Data Index: 4278904 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.5079. Min Act: -0.1700
Data Index: 4125561 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.4454. Min Act: -0.1700
Data Index: 937464 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.4454. Min Act: -0.1700
Data Index: 8187478 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.4141. Min Act: -0.1700
Data Index: 6393202 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.3829. Min Act: -0.1700
Data Index: 2951717 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.3204. Min Act: -0.1700
Data Index: 5409744 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2891. Min Act: -0.1700
Data Index: 6660703 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2266. Min Act: -0.1700
Data Index: 7305249 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2579. Min Act: -0.1700
Data Index: 5760172 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2579. Min Act: -0.1700
Data Index: 1209740 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2891. Min Act: -0.1700
Data Index: 6553284 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2579. Min Act: -0.1700
Data Index: 984345 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2579. Min Act: -0.1700
Data Index: 4646972 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2266. Min Act: -0.1700
Data Index: 2747599 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.2266. Min Act: -0.1700
Data Index: 1478102 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.1954. Min Act: -0.1700
Data Index: 8259218 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.1954. Min Act: -0.1700
Data Index: 6207033 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3204. Min Range: -7.3204
Max Act: 6.1954. Min Act: -0.1700
Data Index: 6817983 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19