Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4681. Min Act: -0.1700
Data Index: 8465496 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4681. Min Act: -0.1700
Data Index: 5012038 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4593. Min Act: -0.1700
Data Index: 8492000 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4329. Min Act: -0.1699
Data Index: 1783558 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4329. Min Act: -0.1700
Data Index: 823333 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4329. Min Act: -0.1700
Data Index: 7078517 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4417. Min Act: -0.1700
Data Index: 2782012 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4153. Min Act: -0.1700
Data Index: 4227284 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4241. Min Act: -0.1700
Data Index: 5557291 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4241. Min Act: -0.1699
Data Index: 1050123 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4329. Min Act: -0.1700
Data Index: 470928 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4241. Min Act: -0.1699
Data Index: 8742511 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4241. Min Act: -0.1700
Data Index: 3159871 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4153. Min Act: -0.1700
Data Index: 540932 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4241. Min Act: -0.1700
Data Index: 8117594 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4065. Min Act: -0.1700
Data Index: 2843844 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4065. Min Act: -0.1623
Data Index: 6117290 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4241. Min Act: -0.1700
Data Index: 4872189 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4065. Min Act: -0.1700
Data Index: 4655558 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4681. Min Range: -1.4681
Max Act: 1.4241. Min Act: -0.1700
Data Index: 381313 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19