Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4606 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.7940. Min Act: -0.1700
Data Index: 1942695 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6376. Min Act: -0.1700
Data Index: 6897586 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5750. Min Act: -0.1700
Data Index: 5196828 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5906. Min Act: -0.1700
Data Index: 5560531 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4967. Min Act: -0.1700
Data Index: 3188965 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4497. Min Act: -0.1700
Data Index: 768073 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4340. Min Act: -0.1700
Data Index: 4901563 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 5052823 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 1135475 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3870. Min Act: -0.1700
Data Index: 3013416 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 1040998 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3870. Min Act: -0.1700
Data Index: 8502283 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3870. Min Act: -0.1700
Data Index: 666919 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3556. Min Act: -0.1700
Data Index: 3442432 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3870. Min Act: -0.1700
Data Index: 282000 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3556. Min Act: -0.1700
Data Index: 5793315 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3556. Min Act: -0.1700
Data Index: 5129547 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3556. Min Act: -0.1700
Data Index: 8605177 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3556. Min Act: -0.1700
Data Index: 2128518 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3085. Min Act: -0.1700
Data Index: 3125277 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19