Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.5162. Min Act: -0.1700
Data Index: 7984078 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.5162. Min Act: -0.1700
Data Index: 1460522 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.4849. Min Act: -0.1700
Data Index: 48003 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.4537. Min Act: -0.1700
Data Index: 6259543 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.4537. Min Act: -0.1700
Data Index: 275817 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.3912. Min Act: -0.1700
Data Index: 8083153 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2974. Min Act: -0.1700
Data Index: 4160107 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2974. Min Act: -0.1700
Data Index: 2978188 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2974. Min Act: -0.1700
Data Index: 8114098 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2974. Min Act: -0.1700
Data Index: 6963215 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2662. Min Act: -0.1700
Data Index: 5849650 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2974. Min Act: -0.1700
Data Index: 2413634 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2662. Min Act: -0.1700
Data Index: 4972239 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2662. Min Act: -0.1700
Data Index: 1567004 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2349. Min Act: -0.1700
Data Index: 6829572 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2349. Min Act: -0.1700
Data Index: 4327376 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2349. Min Act: -0.1700
Data Index: 6288917 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2036. Min Act: -0.1700
Data Index: 7044869 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2036. Min Act: -0.1700
Data Index: 7753468 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5162. Min Range: -4.5162
Max Act: 4.2036. Min Act: -0.1700
Data Index: 3746498 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19