Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.6497. Min Act: -0.1700
Data Index: 3370971 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.6337. Min Act: -0.1700
Data Index: 4624802 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5693. Min Act: -0.1700
Data Index: 158460 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5693. Min Act: -0.1700
Data Index: 3408355 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5532. Min Act: -0.1700
Data Index: 5507060 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5532. Min Act: -0.1700
Data Index: 2995384 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5532. Min Act: -0.1700
Data Index: 1844880 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5370. Min Act: -0.1700
Data Index: 3025567 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5208. Min Act: -0.1700
Data Index: 1972337 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5370. Min Act: -0.1700
Data Index: 6531176 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5370. Min Act: -0.1700
Data Index: 4085775 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5532. Min Act: -0.1700
Data Index: 7683994 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5208. Min Act: -0.1700
Data Index: 776855 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5370. Min Act: -0.1700
Data Index: 1510346 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5047. Min Act: -0.1700
Data Index: 5225199 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5047. Min Act: -0.1700
Data Index: 4203696 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5208. Min Act: -0.1700
Data Index: 2398839 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5208. Min Act: -0.1700
Data Index: 2171186 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5047. Min Act: -0.1700
Data Index: 4077366 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6497. Min Range: -2.6497
Max Act: 2.5047. Min Act: -0.1700
Data Index: 5194674 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19