Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6071 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.8635. Min Act: -0.1700
Data Index: 5108939 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.8635. Min Act: -0.1700
Data Index: 3820996 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.8010. Min Act: -0.1700
Data Index: 1378565 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.7385. Min Act: -0.1700
Data Index: 6291404 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.7385. Min Act: -0.1700
Data Index: 7070010 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.6760. Min Act: -0.1700
Data Index: 6218482 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.5510. Min Act: -0.1700
Data Index: 736290 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.4885. Min Act: -0.1700
Data Index: 8660339 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.3010. Min Act: -0.1700
Data Index: 6555846 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.3010. Min Act: -0.1700
Data Index: 3283613 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.3010. Min Act: -0.1700
Data Index: 3767144 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.3635. Min Act: -0.1700
Data Index: 447038 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.2385. Min Act: -0.1700
Data Index: 1184445 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.2385. Min Act: -0.1700
Data Index: 2802145 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.2385. Min Act: -0.1700
Data Index: 7584143 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.2385. Min Act: -0.1700
Data Index: 6234939 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.3010. Min Act: -0.1700
Data Index: 8359814 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.1760. Min Act: -0.1700
Data Index: 7809790 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.1760. Min Act: -0.1700
Data Index: 936932 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8635. Min Range: -9.8635
Max Act: 9.1760. Min Act: -0.1700
Data Index: 2582630 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19