Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.5999. Min Act: -0.1700
Data Index: 6788126 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.3811. Min Act: -0.1700
Data Index: 693960 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.2561. Min Act: -0.1700
Data Index: 3479302 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.2249. Min Act: -0.1700
Data Index: 1416079 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.1936. Min Act: -0.1700
Data Index: 1095946 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.1311. Min Act: -0.1700
Data Index: 4705065 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.1311. Min Act: -0.1700
Data Index: 7905722 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0686. Min Act: -0.1700
Data Index: 4160536 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0374. Min Act: -0.1700
Data Index: 2637552 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0374. Min Act: -0.1700
Data Index: 1831607 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0374. Min Act: -0.1700
Data Index: 4569235 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0374. Min Act: -0.1700
Data Index: 1227884 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0061. Min Act: -0.1700
Data Index: 6026603 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0061. Min Act: -0.1700
Data Index: 982231 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5999. Min Range: -5.5999
Max Act: 5.0061. Min Act: -0.1700
Data Index: 4919738 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5999. Min Range: -5.5999
Max Act: 4.9749. Min Act: -0.1700
Data Index: 6083205 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5999. Min Range: -5.5999
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2004497 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5999. Min Range: -5.5999
Max Act: 4.9436. Min Act: -0.1700
Data Index: 2218488 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5999. Min Range: -5.5999
Max Act: 4.9436. Min Act: -0.1700
Data Index: 5554008 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5999. Min Range: -5.5999
Max Act: 4.9436. Min Act: -0.1700
Data Index: 461714 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19