Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1497 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 11.0611. Min Range: -11.0611
Max Act: 11.0611. Min Act: -0.1700
Data Index: 2692029 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0611. Min Range: -11.0611
Max Act: 10.1236. Min Act: -0.1700
Data Index: 1721396 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.0611. Min Act: -0.1700
Data Index: 6578145 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.3736. Min Act: -0.1700
Data Index: 5639215 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.1861. Min Act: -0.1700
Data Index: 3749539 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.3736. Min Act: -0.1700
Data Index: 2265795 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.3111. Min Act: -0.1700
Data Index: 5430283 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.2486. Min Act: -0.1700
Data Index: 8581406 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4986. Min Act: -0.1700
Data Index: 8104909 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0611. Min Range: -11.0611
Max Act: 8.2799. Min Act: -0.1700
Data Index: 21857 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4986. Min Act: -0.1700
Data Index: 15296 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4986. Min Act: -0.1700
Data Index: 8296674 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4986. Min Act: -0.1700
Data Index: 8019942 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4986. Min Act: -0.1700
Data Index: 2165472 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4986. Min Act: -0.1700
Data Index: 4181087 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4986. Min Act: -0.1700
Data Index: 3164784 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4361. Min Act: -0.1700
Data Index: 1189511 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.4361. Min Act: -0.1700
Data Index: 492079 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.3736. Min Act: -0.1700
Data Index: 1511384 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0611. Min Range: -11.0611
Max Act: 9.3111. Min Act: -0.1700
Data Index: 1620127 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19