Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4456 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.5290. Min Act: -0.1700
Data Index: 3633258 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4977. Min Act: -0.1700
Data Index: 4557255 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4352. Min Act: -0.1700
Data Index: 3033451 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4352. Min Act: -0.1700
Data Index: 3214370 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4352. Min Act: -0.1700
Data Index: 7075533 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 6359395 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 4028407 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 3184334 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.4040. Min Act: -0.1700
Data Index: 1838506 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3727. Min Act: -0.1700
Data Index: 5733275 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3727. Min Act: -0.1700
Data Index: 2459999 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3727. Min Act: -0.1700
Data Index: 8046967 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 415322 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3727. Min Act: -0.1700
Data Index: 7411342 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 550033 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 7868931 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3415. Min Act: -0.1700
Data Index: 7954183 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4592760 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4557254 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5290. Min Range: -5.5290
Max Act: 5.3102. Min Act: -0.1700
Data Index: 6937462 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19