Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.8708. Min Act: -0.1700
Data Index: 1127067 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.8083. Min Act: -0.1700
Data Index: 5356878 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.8083. Min Act: -0.1700
Data Index: 3600302 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.6833. Min Act: -0.1700
Data Index: 5907748 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.5583. Min Act: -0.1700
Data Index: 4756796 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.5583. Min Act: -0.1700
Data Index: 40862 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.5271. Min Act: -0.1700
Data Index: 7609692 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.5271. Min Act: -0.1700
Data Index: 3806430 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4958. Min Act: -0.1700
Data Index: 4286465 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4333. Min Act: -0.1700
Data Index: 7033519 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4333. Min Act: -0.1700
Data Index: 5195716 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4333. Min Act: -0.1700
Data Index: 7267327 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4333. Min Act: -0.1700
Data Index: 2264125 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4021. Min Act: -0.1700
Data Index: 3421150 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4021. Min Act: -0.1700
Data Index: 7883654 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.3708. Min Act: -0.1700
Data Index: 6986795 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.4021. Min Act: -0.1700
Data Index: 1588619 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.3396. Min Act: -0.1700
Data Index: 7259485 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.3396. Min Act: -0.1700
Data Index: 4000883 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8708. Min Range: -7.8708
Max Act: 7.3083. Min Act: -0.1700
Data Index: 2707399 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19