Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2117 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.4690. Min Act: -0.1700
Data Index: 8509750 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.4065. Min Act: -0.1700
Data Index: 3983316 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.3440. Min Act: -0.1700
Data Index: 6930158 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.2815. Min Act: -0.1700
Data Index: 4493177 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.2190. Min Act: -0.1700
Data Index: 8457066 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1877. Min Act: -0.1700
Data Index: 7916569 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4948173 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1565. Min Act: -0.1700
Data Index: 6132539 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1252. Min Act: -0.1700
Data Index: 2500520 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.1252. Min Act: -0.1700
Data Index: 8175573 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0940. Min Act: -0.1700
Data Index: 3141740 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0627. Min Act: -0.1700
Data Index: 4953025 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0627. Min Act: -0.1700
Data Index: 2210165 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0627. Min Act: -0.1700
Data Index: 1865550 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0627. Min Act: -0.1700
Data Index: 3838807 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0940. Min Act: -0.1700
Data Index: 4592413 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0315. Min Act: -0.1700
Data Index: 9053 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0315. Min Act: -0.1700
Data Index: 4180874 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0002. Min Act: -0.1700
Data Index: 3749073 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4690. Min Range: -5.4690
Max Act: 5.0315. Min Act: -0.1700
Data Index: 603911 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19