Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1872. Min Range: -4.1872
Max Act: 4.1872. Min Act: -0.1700
Data Index: 6687268 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1872. Min Range: -4.1872
Max Act: 4.1247. Min Act: -0.1700
Data Index: 1524628 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.9997. Min Act: -0.1700
Data Index: 4427985 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.9684. Min Act: -0.1700
Data Index: 8345685 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8434. Min Act: -0.1700
Data Index: 1394256 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8434. Min Act: -0.1700
Data Index: 1344095 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8121. Min Act: -0.1700
Data Index: 1140863 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8121. Min Act: -0.1700
Data Index: 3043849 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8121. Min Act: -0.1700
Data Index: 6830619 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8121. Min Act: -0.1700
Data Index: 905119 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8121. Min Act: -0.1700
Data Index: 8695105 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.8121. Min Act: -0.1700
Data Index: 4703976 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7808. Min Act: -0.1700
Data Index: 1566642 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7495. Min Act: -0.1700
Data Index: 3543493 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7495. Min Act: -0.1700
Data Index: 1609798 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7495. Min Act: -0.1700
Data Index: 5463193 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7495. Min Act: -0.1700
Data Index: 79808 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7183. Min Act: -0.1700
Data Index: 972031 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7183. Min Act: -0.1700
Data Index: 4095199 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1872. Min Range: -4.1872
Max Act: 3.7183. Min Act: -0.1700
Data Index: 6311682 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19