Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.6364. Min Act: -0.1700
Data Index: 5889636 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.5739. Min Act: -0.1700
Data Index: 1038454 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.5114. Min Act: -0.1700
Data Index: 6946094 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.5114. Min Act: -0.1700
Data Index: 7695487 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.4801. Min Act: -0.1700
Data Index: 4395497 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.4489. Min Act: -0.1700
Data Index: 7080946 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.4489. Min Act: -0.1700
Data Index: 8803864 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 1197738 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.4176. Min Act: -0.1700
Data Index: 6818513 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 4512607 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 7215991 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 1916064 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 4108865 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 6004262 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 957954 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 298010 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3864. Min Act: -0.1700
Data Index: 2047132 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3551. Min Act: -0.1700
Data Index: 8464392 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3551. Min Act: -0.1700
Data Index: 4257161 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6364. Min Range: -4.6364
Max Act: 4.3239. Min Act: -0.1700
Data Index: 6551607 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19