Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2083 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5713. Min Range: -6.5713
Max Act: 6.5713. Min Act: -0.1700
Data Index: 5010459 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5713. Min Range: -6.5713
Max Act: 6.3525. Min Act: -0.1700
Data Index: 8048468 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5713. Min Range: -6.5713
Max Act: 6.1650. Min Act: -0.1700
Data Index: 422230 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5713. Min Range: -6.5713
Max Act: 6.1650. Min Act: -0.1700
Data Index: 6285343 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5713. Min Range: -6.5713
Max Act: 6.0088. Min Act: -0.1700
Data Index: 4429347 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.9150. Min Act: -0.1700
Data Index: 6676440 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.9463. Min Act: -0.1700
Data Index: 8070048 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.9150. Min Act: -0.1700
Data Index: 6354647 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.8525. Min Act: -0.1700
Data Index: 5875261 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.8213. Min Act: -0.1700
Data Index: 5029230 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.7588. Min Act: -0.1700
Data Index: 7768642 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.7588. Min Act: -0.1700
Data Index: 6529711 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.7588. Min Act: -0.1700
Data Index: 7676223 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.7275. Min Act: -0.1700
Data Index: 7048606 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.7275. Min Act: -0.1700
Data Index: 572879 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.6963. Min Act: -0.1700
Data Index: 8274709 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.6650. Min Act: -0.1700
Data Index: 2498089 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.6650. Min Act: -0.1700
Data Index: 5295367 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.6650. Min Act: -0.1700
Data Index: 1325141 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5713. Min Range: -6.5713
Max Act: 5.6650. Min Act: -0.1700
Data Index: 1141359 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19