Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1588 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.5537. Min Act: -0.1700
Data Index: 7367166 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.5224. Min Act: -0.1700
Data Index: 2908938 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.3037. Min Act: -0.1700
Data Index: 5869487 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 354343 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 6970502 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1162. Min Act: -0.1700
Data Index: 2191579 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 2256622 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 8072383 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 8496166 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 3867642 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 3007988 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0537. Min Act: -0.1700
Data Index: 972150 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0224. Min Act: -0.1700
Data Index: 7529463 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0224. Min Act: -0.1700
Data Index: 4329447 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0224. Min Act: -0.1700
Data Index: 2594008 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5537. Min Range: -5.5537
Max Act: 4.9912. Min Act: -0.1700
Data Index: 4586549 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5537. Min Range: -5.5537
Max Act: 4.9912. Min Act: -0.1700
Data Index: 6660280 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5537. Min Range: -5.5537
Max Act: 4.9912. Min Act: -0.1700
Data Index: 1251267 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5537. Min Range: -5.5537
Max Act: 4.9912. Min Act: -0.1700
Data Index: 65609 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5537. Min Range: -5.5537
Max Act: 4.9912. Min Act: -0.1700
Data Index: 6098929 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19