Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2904. Min Range: -8.2904
Max Act: 8.2904. Min Act: -0.1700
Data Index: 2838526 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2904. Min Range: -8.2904
Max Act: 8.2279. Min Act: -0.1700
Data Index: 5986920 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.9466. Min Act: -0.1700
Data Index: 3026616 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.9154. Min Act: -0.1700
Data Index: 1840019 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.8841. Min Act: -0.1700
Data Index: 7979800 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.7904. Min Act: -0.1700
Data Index: 8105944 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.7591. Min Act: -0.1700
Data Index: 1453965 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.7279. Min Act: -0.1700
Data Index: 3317486 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.7279. Min Act: -0.1700
Data Index: 274468 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.6966. Min Act: -0.1700
Data Index: 5159966 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.6966. Min Act: -0.1700
Data Index: 2156884 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.6966. Min Act: -0.1700
Data Index: 8248696 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.6341. Min Act: -0.1700
Data Index: 1638674 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.6341. Min Act: -0.1700
Data Index: 4380358 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.6029. Min Act: -0.1700
Data Index: 6924349 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.6029. Min Act: -0.1700
Data Index: 8768962 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.5716. Min Act: -0.1700
Data Index: 6851918 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.5404. Min Act: -0.1700
Data Index: 2775644 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.5716. Min Act: -0.1700
Data Index: 7409639 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2904. Min Range: -8.2904
Max Act: 7.5404. Min Act: -0.1700
Data Index: 6569362 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19