Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6343 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.3404. Min Act: -0.1700
Data Index: 8342676 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.3092. Min Act: -0.1700
Data Index: 2817890 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.1842. Min Act: -0.1700
Data Index: 2841738 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.1842. Min Act: -0.1700
Data Index: 5880947 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.1529. Min Act: -0.1700
Data Index: 5884779 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.1529. Min Act: -0.1700
Data Index: 7965600 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.0592. Min Act: -0.1700
Data Index: 3504082 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.0592. Min Act: -0.1700
Data Index: 6834683 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9967. Min Act: -0.1700
Data Index: 6399792 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9654. Min Act: -0.1700
Data Index: 6911438 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9967. Min Act: -0.1700
Data Index: 7646896 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3404. Min Range: -7.3404
Max Act: 7.0279. Min Act: -0.1700
Data Index: 5310668 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9654. Min Act: -0.1700
Data Index: 5560681 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9967. Min Act: -0.1700
Data Index: 2850096 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9342. Min Act: -0.1700
Data Index: 5632027 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9029. Min Act: -0.1700
Data Index: 2189924 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.9029. Min Act: -0.1700
Data Index: 6393126 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.8717. Min Act: -0.1700
Data Index: 2702730 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.8717. Min Act: -0.1700
Data Index: 3400940 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3404. Min Range: -7.3404
Max Act: 6.8717. Min Act: -0.1700
Data Index: 1060077 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19