Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2558 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.7431. Min Act: -0.1700
Data Index: 8239167 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2329592 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.6493. Min Act: -0.1700
Data Index: 6406711 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.6181. Min Act: -0.1700
Data Index: 430212 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.6181. Min Act: -0.1700
Data Index: 5941844 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.6181. Min Act: -0.1700
Data Index: 4285071 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.5556. Min Act: -0.1700
Data Index: 2762912 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.5243. Min Act: -0.1700
Data Index: 965457 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.4931. Min Act: -0.1700
Data Index: 5838600 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.4306. Min Act: -0.1700
Data Index: 1753299 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.4618. Min Act: -0.1700
Data Index: 1984593 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.4618. Min Act: -0.1700
Data Index: 2077618 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3993. Min Act: -0.1700
Data Index: 5065803 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3993. Min Act: -0.1700
Data Index: 3095736 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3993. Min Act: -0.1700
Data Index: 5052308 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3993. Min Act: -0.1700
Data Index: 2328129 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3681. Min Act: -0.1700
Data Index: 4890996 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3368. Min Act: -0.1700
Data Index: 1339659 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3681. Min Act: -0.1700
Data Index: 5053001 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7431. Min Range: -4.7431
Max Act: 4.3368. Min Act: -0.1700
Data Index: 3715040 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19