Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0348. Min Range: -4.0348
Max Act: 4.0035. Min Act: -0.1700
Data Index: 2509112 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0348. Min Range: -4.0348
Max Act: 4.0035. Min Act: -0.1700
Data Index: 5490504 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9723. Min Act: -0.1700
Data Index: 4378709 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0348. Min Range: -4.0348
Max Act: 4.0348. Min Act: -0.1700
Data Index: 3374624 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9410. Min Act: -0.1700
Data Index: 4738863 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9410. Min Act: -0.1700
Data Index: 8179349 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9410. Min Act: -0.1700
Data Index: 1203518 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9097. Min Act: -0.1700
Data Index: 7376361 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9097. Min Act: -0.1700
Data Index: 169591 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9097. Min Act: -0.1700
Data Index: 1005983 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9097. Min Act: -0.1700
Data Index: 3846889 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.9097. Min Act: -0.1700
Data Index: 2525616 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8785. Min Act: -0.1700
Data Index: 8015048 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 6236074 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 8811650 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 4818024 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 4405978 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8472. Min Act: -0.1700
Data Index: 1300480 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8159. Min Act: -0.1700
Data Index: 4950300 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0348. Min Range: -4.0348
Max Act: 3.8159. Min Act: -0.1700
Data Index: 3354300 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19