Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2564. Min Range: -5.2564
Max Act: 5.2564. Min Act: -0.1700
Data Index: 348473 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2564. Min Range: -5.2564
Max Act: 5.1001. Min Act: -0.1700
Data Index: 6849487 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2564. Min Range: -5.2564
Max Act: 5.0689. Min Act: -0.1700
Data Index: 4713827 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2564. Min Range: -5.2564
Max Act: 5.0689. Min Act: -0.1700
Data Index: 3754951 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2564. Min Range: -5.2564
Max Act: 5.0064. Min Act: -0.1700
Data Index: 4474352 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.9751. Min Act: -0.1700
Data Index: 2812995 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2564. Min Range: -5.2564
Max Act: 5.0064. Min Act: -0.1700
Data Index: 4474349 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2564. Min Range: -5.2564
Max Act: 5.0376. Min Act: -0.1700
Data Index: 2728996 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.9751. Min Act: -0.1700
Data Index: 1114667 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.9439. Min Act: -0.1700
Data Index: 6318022 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8814. Min Act: -0.1700
Data Index: 6592716 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8501. Min Act: -0.1700
Data Index: 4914646 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8814. Min Act: -0.1700
Data Index: 8433284 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8814. Min Act: -0.1700
Data Index: 7910682 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8189. Min Act: -0.1700
Data Index: 8183934 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8189. Min Act: -0.1700
Data Index: 5725652 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8189. Min Act: -0.1700
Data Index: 837506 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.8189. Min Act: -0.1700
Data Index: 1928947 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.7876. Min Act: -0.1700
Data Index: 5553269 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2564. Min Range: -5.2564
Max Act: 4.7876. Min Act: -0.1700
Data Index: 4594524 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19