Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3228 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.7905. Min Act: -0.1700
Data Index: 6755998 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.7592. Min Act: -0.1700
Data Index: 726820 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.7592. Min Act: -0.1700
Data Index: 3733901 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.7592. Min Act: -0.1700
Data Index: 9014 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.7280. Min Act: -0.1700
Data Index: 3945376 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.5717. Min Act: -0.1700
Data Index: 7988667 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.5717. Min Act: -0.1700
Data Index: 7031557 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.5092. Min Act: -0.1700
Data Index: 3211533 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.4467. Min Act: -0.1700
Data Index: 6008314 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.3842. Min Act: -0.1700
Data Index: 5719358 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.3217. Min Act: -0.1700
Data Index: 52765 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.2905. Min Act: -0.1700
Data Index: 6008315 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.2905. Min Act: -0.1700
Data Index: 4410610 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.2592. Min Act: -0.1700
Data Index: 3744472 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.2280. Min Act: -0.1700
Data Index: 114901 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.2280. Min Act: -0.1700
Data Index: 6896083 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.2280. Min Act: -0.1700
Data Index: 4577147 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.1655. Min Act: -0.1700
Data Index: 6667054 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.1655. Min Act: -0.1700
Data Index: 6765639 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7905. Min Range: -7.7905
Max Act: 7.1030. Min Act: -0.1700
Data Index: 7360686 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19