Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.2490. Min Act: -0.1700
Data Index: 6435177 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.1232. Min Act: -0.1700
Data Index: 321588 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.1074. Min Act: -0.1700
Data Index: 5162283 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.1074. Min Act: -0.1700
Data Index: 182783 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.1074. Min Act: -0.1700
Data Index: 7830659 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.0601. Min Act: -0.1700
Data Index: 8814643 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.0601. Min Act: -0.1700
Data Index: 4131583 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.0285. Min Act: -0.1700
Data Index: 4811802 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.0285. Min Act: -0.1700
Data Index: 1481586 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.0443. Min Act: -0.1700
Data Index: 4168301 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2490. Min Range: -3.2490
Max Act: 3.0128. Min Act: -0.1700
Data Index: 3882751 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9970. Min Act: -0.1700
Data Index: 7814192 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9970. Min Act: -0.1700
Data Index: 183218 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9811. Min Act: -0.1700
Data Index: 4903940 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9811. Min Act: -0.1700
Data Index: 8688125 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9495. Min Act: -0.1700
Data Index: 4131584 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9653. Min Act: -0.1700
Data Index: 301356 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9653. Min Act: -0.1700
Data Index: 8297314 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9337. Min Act: -0.1700
Data Index: 4272184 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2490. Min Range: -3.2490
Max Act: 2.9495. Min Act: -0.1700
Data Index: 7610104 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19