Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.5953. Min Act: -0.1700
Data Index: 3730812 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.4390. Min Act: -0.1700
Data Index: 5869312 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.3453. Min Act: -0.1700
Data Index: 8064452 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.3453. Min Act: -0.1700
Data Index: 4131241 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.3453. Min Act: -0.1700
Data Index: 4569968 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.3140. Min Act: -0.1700
Data Index: 3730813 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.3140. Min Act: -0.1700
Data Index: 6044511 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.2828. Min Act: -0.1700
Data Index: 4329426 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.2828. Min Act: -0.1700
Data Index: 4794417 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.2828. Min Act: -0.1700
Data Index: 2621188 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.2515. Min Act: -0.1700
Data Index: 745114 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1890. Min Act: -0.1700
Data Index: 4186963 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1890. Min Act: -0.1700
Data Index: 4635912 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1578. Min Act: -0.1700
Data Index: 5252555 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1578. Min Act: -0.1700
Data Index: 8665098 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1578. Min Act: -0.1700
Data Index: 6467060 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5852433 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1578. Min Act: -0.1700
Data Index: 5812894 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1265. Min Act: -0.1700
Data Index: 7102538 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5953. Min Range: -5.5953
Max Act: 5.1265. Min Act: -0.1700
Data Index: 7519238 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19