Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3873 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.4544. Min Act: -0.1700
Data Index: 5823123 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.2669. Min Act: -0.1700
Data Index: 4066546 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.2356. Min Act: -0.1700
Data Index: 8663644 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.1731. Min Act: -0.1700
Data Index: 7653038 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.1731. Min Act: -0.1700
Data Index: 6981984 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.1731. Min Act: -0.1700
Data Index: 3117829 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.1419. Min Act: -0.1700
Data Index: 5571883 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.1419. Min Act: -0.1700
Data Index: 3559304 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.1106. Min Act: -0.1700
Data Index: 1782208 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.1106. Min Act: -0.1700
Data Index: 8418992 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.0794. Min Act: -0.1700
Data Index: 1564918 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.0794. Min Act: -0.1700
Data Index: 91585 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.0794. Min Act: -0.1700
Data Index: 6177024 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.0481. Min Act: -0.1700
Data Index: 3185609 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4544. Min Range: -6.4544
Max Act: 6.0481. Min Act: -0.1700
Data Index: 4912161 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.9856. Min Act: -0.1700
Data Index: 6073857 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.9544. Min Act: -0.1700
Data Index: 708436 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.9544. Min Act: -0.1700
Data Index: 5738639 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.9544. Min Act: -0.1700
Data Index: 6401122 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4544. Min Range: -6.4544
Max Act: 5.9856. Min Act: -0.1700
Data Index: 2253759 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19