Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1268 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.9329. Min Act: -0.1700
Data Index: 5177485 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8733. Min Act: -0.1700
Data Index: 3427168 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8903. Min Act: -0.1700
Data Index: 1685379 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8476. Min Act: -0.1700
Data Index: 1626541 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.9754. Min Act: -0.1700
Data Index: 3036379 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8733. Min Act: -0.1700
Data Index: 1770998 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8818. Min Act: -0.1700
Data Index: 2526314 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8476. Min Act: -0.1700
Data Index: 7232164 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7961. Min Act: -0.1700
Data Index: 6594269 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8133. Min Act: -0.1700
Data Index: 882084 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.8133. Min Act: -0.1700
Data Index: 1681456 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7961. Min Act: -0.1700
Data Index: 4072891 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7788. Min Act: -0.1700
Data Index: 294844 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7788. Min Act: -0.1700
Data Index: 8035391 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7616. Min Act: -0.1700
Data Index: 7835929 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7530. Min Act: -0.1700
Data Index: 1960936 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7530. Min Act: -0.1700
Data Index: 4482773 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7010. Min Act: -0.1700
Data Index: 8638888 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7530. Min Act: -0.1700
Data Index: 5468481 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9754. Min Range: -1.9754
Max Act: 1.7270. Min Act: -0.1700
Data Index: 72600 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19