Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.5388. Min Act: -0.1700
Data Index: 1200518 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.3826. Min Act: -0.1700
Data Index: 2121146 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.2888. Min Act: -0.1700
Data Index: 4138740 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.1326. Min Act: -0.1700
Data Index: 7687934 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.1326. Min Act: -0.1700
Data Index: 8391131 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.1326. Min Act: -0.1700
Data Index: 6182798 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.1013. Min Act: -0.1700
Data Index: 2147588 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.0076. Min Act: -0.1700
Data Index: 2081612 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.0388. Min Act: -0.1700
Data Index: 4745988 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5388. Min Range: -6.5388
Max Act: 6.0076. Min Act: -0.1700
Data Index: 7940579 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9763. Min Act: -0.1700
Data Index: 7651484 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9763. Min Act: -0.1700
Data Index: 2795237 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9451. Min Act: -0.1700
Data Index: 5697985 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9451. Min Act: -0.1700
Data Index: 5351149 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9138. Min Act: -0.1700
Data Index: 4153790 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9138. Min Act: -0.1700
Data Index: 1288030 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9138. Min Act: -0.1700
Data Index: 6643174 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9138. Min Act: -0.1700
Data Index: 1478119 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.8826. Min Act: -0.1700
Data Index: 1292288 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5388. Min Range: -6.5388
Max Act: 5.9138. Min Act: -0.1700
Data Index: 5623136 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19