Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2953 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 5918948 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.7213. Min Act: -0.1700
Data Index: 6440423 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.7213. Min Act: -0.1700
Data Index: 4274628 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 8494362 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 8484807 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 7686707 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 3915088 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 6531548 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 689829 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6900. Min Act: -0.1700
Data Index: 1065643 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 1372319 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 8002330 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 4117144 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 6531545 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 4041743 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 6336947 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 3435179 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 6092484 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6587. Min Act: -0.1700
Data Index: 1372276 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7213. Min Range: -3.7213
Max Act: 3.6274. Min Act: -0.1700
Data Index: 1767456 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19