Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6306 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2736. Min Range: -6.2736
Max Act: 6.2736. Min Act: -0.1700
Data Index: 63781 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2736. Min Range: -6.2736
Max Act: 6.2423. Min Act: -0.1700
Data Index: 240789 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2736. Min Range: -6.2736
Max Act: 6.1798. Min Act: -0.1700
Data Index: 5763796 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2736. Min Range: -6.2736
Max Act: 6.1798. Min Act: -0.1700
Data Index: 2220207 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2736. Min Range: -6.2736
Max Act: 6.1486. Min Act: -0.1700
Data Index: 7693091 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2736. Min Range: -6.2736
Max Act: 6.0861. Min Act: -0.1700
Data Index: 5170614 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.9923. Min Act: -0.1700
Data Index: 6304096 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.9923. Min Act: -0.1700
Data Index: 3032486 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.9611. Min Act: -0.1700
Data Index: 2750031 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.9298. Min Act: -0.1700
Data Index: 1971040 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.8673. Min Act: -0.1700
Data Index: 3594975 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.8673. Min Act: -0.1700
Data Index: 7836686 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.8361. Min Act: -0.1700
Data Index: 128736 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.7736. Min Act: -0.1700
Data Index: 1390222 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.7736. Min Act: -0.1700
Data Index: 5027860 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.7736. Min Act: -0.1700
Data Index: 4115236 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.7736. Min Act: -0.1700
Data Index: 6304097 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.7736. Min Act: -0.1700
Data Index: 2934854 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.7736. Min Act: -0.1700
Data Index: 6201352 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2736. Min Range: -6.2736
Max Act: 5.7423. Min Act: -0.1700
Data Index: 3379587 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19