Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 820 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.1651. Min Act: -0.1700
Data Index: 5673550 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.1026. Min Act: -0.1700
Data Index: 384756 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.1339. Min Act: -0.1700
Data Index: 4518880 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.1026. Min Act: -0.1700
Data Index: 3151778 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4413631 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.0401. Min Act: -0.1700
Data Index: 3063681 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.0089. Min Act: -0.1700
Data Index: 8423408 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.0089. Min Act: -0.1700
Data Index: 6213529 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.0089. Min Act: -0.1700
Data Index: 127197 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1651. Min Range: -5.1651
Max Act: 5.0089. Min Act: -0.1700
Data Index: 7381903 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9151. Min Act: -0.1700
Data Index: 4862499 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9464. Min Act: -0.1700
Data Index: 7538527 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9151. Min Act: -0.1700
Data Index: 2910318 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9151. Min Act: -0.1700
Data Index: 2844928 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9151. Min Act: -0.1700
Data Index: 2092386 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9464. Min Act: -0.1700
Data Index: 765383 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9151. Min Act: -0.1700
Data Index: 416694 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9151. Min Act: -0.1700
Data Index: 6006342 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.9151. Min Act: -0.1700
Data Index: 7039143 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1651. Min Range: -5.1651
Max Act: 4.8839. Min Act: -0.1700
Data Index: 6598085 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19