Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1212. Min Range: -4.1212
Max Act: 4.1212. Min Act: -0.1700
Data Index: 5476332 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1212. Min Range: -4.1212
Max Act: 4.0899. Min Act: -0.1700
Data Index: 5476333 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.9649. Min Act: -0.1700
Data Index: 7770479 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.9336. Min Act: -0.1700
Data Index: 4035101 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.7773. Min Act: -0.1700
Data Index: 1946349 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.7460. Min Act: -0.1700
Data Index: 8447013 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.7773. Min Act: -0.1700
Data Index: 4702731 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.7147. Min Act: -0.1700
Data Index: 140986 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.7147. Min Act: -0.1700
Data Index: 6615924 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6834. Min Act: -0.1700
Data Index: 360580 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6678. Min Act: -0.1700
Data Index: 2293044 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6834. Min Act: -0.1700
Data Index: 7428804 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6521. Min Act: -0.1700
Data Index: 4470770 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6521. Min Act: -0.1700
Data Index: 2934295 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6365. Min Act: -0.1700
Data Index: 6137922 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6365. Min Act: -0.1700
Data Index: 260154 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6521. Min Act: -0.1700
Data Index: 8414106 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6208. Min Act: -0.1700
Data Index: 2324971 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.6052. Min Act: -0.1700
Data Index: 1360614 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1212. Min Range: -4.1212
Max Act: 3.5582. Min Act: -0.1700
Data Index: 8364089 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19