Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 616 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.7099. Min Act: -0.1700
Data Index: 3900227 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.6003. Min Act: -0.1700
Data Index: 6153856 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.5064. Min Act: -0.1700
Data Index: 4181484 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.4751. Min Act: -0.1700
Data Index: 7730057 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.4907. Min Act: -0.1700
Data Index: 2857135 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.4437. Min Act: -0.1700
Data Index: 8767025 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.4124. Min Act: -0.1700
Data Index: 5138409 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.3810. Min Act: -0.1700
Data Index: 3370005 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.4124. Min Act: -0.1700
Data Index: 1581969 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.3653. Min Act: -0.1700
Data Index: 3943188 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.3497. Min Act: -0.1700
Data Index: 2438651 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.3340. Min Act: -0.1700
Data Index: 7373785 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.3340. Min Act: -0.1700
Data Index: 1689538 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.2712. Min Act: -0.1700
Data Index: 6265889 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.3026. Min Act: -0.1700
Data Index: 1538205 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.2555. Min Act: -0.1700
Data Index: 2000731 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.2240. Min Act: -0.1700
Data Index: 714089 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.2083. Min Act: -0.1700
Data Index: 2585220 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.1926. Min Act: -0.1700
Data Index: 4905420 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7099. Min Range: -3.7099
Max Act: 3.2083. Min Act: -0.1700
Data Index: 7712520 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19