Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 304 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.4996. Min Act: -0.1700
Data Index: 5867718 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.4058. Min Act: -0.1700
Data Index: 7456338 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.4058. Min Act: -0.1700
Data Index: 4510810 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3746. Min Act: -0.1700
Data Index: 979255 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3433. Min Act: -0.1700
Data Index: 995373 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3121. Min Act: -0.1700
Data Index: 4287970 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3121. Min Act: -0.1700
Data Index: 6654973 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.3121. Min Act: -0.1700
Data Index: 7460967 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2808. Min Act: -0.1700
Data Index: 6381794 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2808. Min Act: -0.1700
Data Index: 798927 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2183. Min Act: -0.1700
Data Index: 5287222 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2496. Min Act: -0.1700
Data Index: 2913178 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2496. Min Act: -0.1700
Data Index: 4063410 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2183. Min Act: -0.1700
Data Index: 3492811 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.2496. Min Act: -0.1700
Data Index: 23528 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.1871. Min Act: -0.1700
Data Index: 5815378 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.1871. Min Act: -0.1700
Data Index: 6578080 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.1871. Min Act: -0.1700
Data Index: 545803 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.1871. Min Act: -0.1700
Data Index: 8091106 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4996. Min Range: -5.4996
Max Act: 5.1558. Min Act: -0.1700
Data Index: 7165005 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19