Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 473 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1194. Min Range: -6.1194
Max Act: 6.1194. Min Act: -0.1700
Data Index: 2529175 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1194. Min Range: -6.1194
Max Act: 6.0881. Min Act: -0.1700
Data Index: 295284 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1194. Min Range: -6.1194
Max Act: 6.0569. Min Act: -0.1700
Data Index: 1622370 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.9944. Min Act: -0.1700
Data Index: 5787521 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.9944. Min Act: -0.1700
Data Index: 960336 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1238310 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1229832 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.9319. Min Act: -0.1700
Data Index: 7759934 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.9319. Min Act: -0.1700
Data Index: 2577838 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8694. Min Act: -0.1700
Data Index: 6125513 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8381. Min Act: -0.1700
Data Index: 2640127 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8381. Min Act: -0.1700
Data Index: 224271 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8381. Min Act: -0.1700
Data Index: 6646400 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8069. Min Act: -0.1700
Data Index: 4887806 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8069. Min Act: -0.1700
Data Index: 2918193 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8069. Min Act: -0.1700
Data Index: 759160 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.7756. Min Act: -0.1700
Data Index: 3138789 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8069. Min Act: -0.1700
Data Index: 4246408 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.8381. Min Act: -0.1700
Data Index: 6646397 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1194. Min Range: -6.1194
Max Act: 5.7756. Min Act: -0.1700
Data Index: 2587936 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19