Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.7436. Min Act: -0.1700
Data Index: 3544460 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.5249. Min Act: -0.1700
Data Index: 2996459 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.4936. Min Act: -0.1700
Data Index: 3167863 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.3686. Min Act: -0.1700
Data Index: 8096412 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.3686. Min Act: -0.1700
Data Index: 569531 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.3374. Min Act: -0.1700
Data Index: 7626558 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.3374. Min Act: -0.1700
Data Index: 5773009 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.3374. Min Act: -0.1700
Data Index: 953261 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.2124. Min Act: -0.1700
Data Index: 7229345 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.2436. Min Act: -0.1700
Data Index: 3892538 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.2436. Min Act: -0.1700
Data Index: 4480219 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.2124. Min Act: -0.1700
Data Index: 3121911 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1499. Min Act: -0.1700
Data Index: 1589409 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1499. Min Act: -0.1700
Data Index: 157979 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1811. Min Act: -0.1700
Data Index: 1206443 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1186. Min Act: -0.1700
Data Index: 7535078 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1186. Min Act: -0.1700
Data Index: 1140124 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1186. Min Act: -0.1700
Data Index: 3849045 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1186. Min Act: -0.1700
Data Index: 1255890 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7436. Min Range: -6.7436
Max Act: 6.1499. Min Act: -0.1700
Data Index: 8092458 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19