Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4935 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5121. Min Range: -7.5121
Max Act: 7.5121. Min Act: -0.1700
Data Index: 7932714 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5121. Min Range: -7.5121
Max Act: 7.2308. Min Act: -0.1700
Data Index: 3044554 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5121. Min Range: -7.5121
Max Act: 7.1371. Min Act: -0.1700
Data Index: 2227094 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5121. Min Range: -7.5121
Max Act: 7.0433. Min Act: -0.1700
Data Index: 7497443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5121. Min Range: -7.5121
Max Act: 7.0121. Min Act: -0.1700
Data Index: 5045123 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.7621. Min Act: -0.1700
Data Index: 413260 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.7933. Min Act: -0.1700
Data Index: 7508035 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.7308. Min Act: -0.1700
Data Index: 1198290 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.7308. Min Act: -0.1700
Data Index: 5205423 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.6996. Min Act: -0.1700
Data Index: 5556635 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.6058. Min Act: -0.1700
Data Index: 1083971 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.6058. Min Act: -0.1700
Data Index: 2175771 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.6371. Min Act: -0.1700
Data Index: 3638282 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.5746. Min Act: -0.1700
Data Index: 6095746 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.5746. Min Act: -0.1700
Data Index: 3667900 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.5433. Min Act: -0.1700
Data Index: 7894975 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.5121. Min Act: -0.1700
Data Index: 8495519 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.4808. Min Act: -0.1700
Data Index: 2933154 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.4808. Min Act: -0.1700
Data Index: 5416838 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5121. Min Range: -7.5121
Max Act: 6.4496. Min Act: -0.1700
Data Index: 3695107 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19