Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0256. Min Range: -7.0256
Max Act: 7.0256. Min Act: -0.1700
Data Index: 5694704 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.9943. Min Act: -0.1700
Data Index: 1684451 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.9631. Min Act: -0.1700
Data Index: 3000041 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.9006. Min Act: -0.1700
Data Index: 4332959 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.7131. Min Act: -0.1700
Data Index: 6786392 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.7443. Min Act: -0.1700
Data Index: 4686533 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.7131. Min Act: -0.1700
Data Index: 2683852 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.6818. Min Act: -0.1700
Data Index: 7963070 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.6818. Min Act: -0.1700
Data Index: 6908041 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.6818. Min Act: -0.1700
Data Index: 5663693 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.6818. Min Act: -0.1700
Data Index: 6748267 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.5881. Min Act: -0.1700
Data Index: 734180 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.6193. Min Act: -0.1700
Data Index: 8086984 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.6193. Min Act: -0.1700
Data Index: 6091634 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.6193. Min Act: -0.1700
Data Index: 2476290 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.5881. Min Act: -0.1700
Data Index: 2633602 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.5881. Min Act: -0.1700
Data Index: 8385647 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.5881. Min Act: -0.1700
Data Index: 6268184 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.5568. Min Act: -0.1700
Data Index: 5088530 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0256. Min Range: -7.0256
Max Act: 6.5568. Min Act: -0.1700
Data Index: 202686 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19