Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4823 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.8073. Min Act: -0.1700
Data Index: 8369753 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.7448. Min Act: -0.1700
Data Index: 3822234 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4635. Min Act: -0.1700
Data Index: 8550477 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4635. Min Act: -0.1700
Data Index: 643130 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4635. Min Act: -0.1700
Data Index: 4613751 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.3698. Min Act: -0.1700
Data Index: 7653133 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.3698. Min Act: -0.1700
Data Index: 7498477 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.4010. Min Act: -0.1700
Data Index: 3883580 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.3385. Min Act: -0.1700
Data Index: 1345044 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.3073. Min Act: -0.1700
Data Index: 3122163 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.3073. Min Act: -0.1700
Data Index: 4658678 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.3073. Min Act: -0.1700
Data Index: 3131474 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.3073. Min Act: -0.1700
Data Index: 24616 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.2448. Min Act: -0.1700
Data Index: 6845715 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.2448. Min Act: -0.1700
Data Index: 3184875 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.2135. Min Act: -0.1700
Data Index: 7725188 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.2135. Min Act: -0.1700
Data Index: 4316337 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.2135. Min Act: -0.1700
Data Index: 5296084 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.2135. Min Act: -0.1700
Data Index: 7447598 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8073. Min Range: -5.8073
Max Act: 5.1823. Min Act: -0.1700
Data Index: 1710924 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19