Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.4429. Min Act: -0.1700
Data Index: 1118532 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.3179. Min Act: -0.1700
Data Index: 6441792 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.1929. Min Act: -0.1700
Data Index: 3938181 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.2241. Min Act: -0.1700
Data Index: 4511555 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.1929. Min Act: -0.1700
Data Index: 6679355 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.1304. Min Act: -0.1700
Data Index: 4643703 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.1304. Min Act: -0.1700
Data Index: 309680 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0991. Min Act: -0.1700
Data Index: 2510655 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0679. Min Act: -0.1700
Data Index: 8297397 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0679. Min Act: -0.1700
Data Index: 1854395 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0366. Min Act: -0.1700
Data Index: 334437 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0366. Min Act: -0.1700
Data Index: 3241909 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0054. Min Act: -0.1700
Data Index: 4535690 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0366. Min Act: -0.1700
Data Index: 2687021 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0679. Min Act: -0.1700
Data Index: 346737 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0054. Min Act: -0.1700
Data Index: 1746158 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0054. Min Act: -0.1700
Data Index: 6216581 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4429. Min Range: -6.4429
Max Act: 5.9741. Min Act: -0.1700
Data Index: 1411930 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0054. Min Act: -0.1700
Data Index: 591150 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4429. Min Range: -6.4429
Max Act: 6.0054. Min Act: -0.1700
Data Index: 5021639 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19