Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1303 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.3291. Min Act: -0.1700
Data Index: 2375632 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.3291. Min Act: -0.1700
Data Index: 8150671 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.2041. Min Act: -0.1700
Data Index: 4802178 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.1416. Min Act: -0.1700
Data Index: 5331910 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.1416. Min Act: -0.1700
Data Index: 6628560 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.1728. Min Act: -0.1700
Data Index: 3459028 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.1416. Min Act: -0.1700
Data Index: 159011 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0791. Min Act: -0.1700
Data Index: 1777483 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0791. Min Act: -0.1700
Data Index: 7103284 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0791. Min Act: -0.1700
Data Index: 487750 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0791. Min Act: -0.1700
Data Index: 6417528 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0478. Min Act: -0.1700
Data Index: 7877548 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0478. Min Act: -0.1700
Data Index: 4212168 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0478. Min Act: -0.1700
Data Index: 5758290 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0478. Min Act: -0.1700
Data Index: 5475360 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0166. Min Act: -0.1700
Data Index: 5442304 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0478. Min Act: -0.1700
Data Index: 922112 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0166. Min Act: -0.1700
Data Index: 7651239 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0166. Min Act: -0.1700
Data Index: 4951725 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3291. Min Range: -5.3291
Max Act: 5.0166. Min Act: -0.1700
Data Index: 3305354 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19