Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.9568. Min Act: -0.1700
Data Index: 3914374 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.5505. Min Act: -0.1700
Data Index: 2353150 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3630. Min Act: -0.1700
Data Index: 2425127 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3630. Min Act: -0.1700
Data Index: 3915264 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3630. Min Act: -0.1700
Data Index: 3387488 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3630. Min Act: -0.1700
Data Index: 3914053 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3318. Min Act: -0.1700
Data Index: 5006262 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3318. Min Act: -0.1700
Data Index: 5911846 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3318. Min Act: -0.1700
Data Index: 2595227 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3318. Min Act: -0.1700
Data Index: 1984355 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3318. Min Act: -0.1700
Data Index: 7540834 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3318. Min Act: -0.1700
Data Index: 886664 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3005. Min Act: -0.1700
Data Index: 1741985 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3005. Min Act: -0.1700
Data Index: 5022608 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.3318. Min Act: -0.1700
Data Index: 6376925 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.2693. Min Act: -0.1700
Data Index: 257468 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.2693. Min Act: -0.1700
Data Index: 5966821 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.2693. Min Act: -0.1700
Data Index: 2303096 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.2693. Min Act: -0.1700
Data Index: 6146251 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9568. Min Range: -5.9568
Max Act: 5.2380. Min Act: -0.1700
Data Index: 3094550 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19