Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.7543. Min Act: -0.1700
Data Index: 5662625 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.6918. Min Act: -0.1700
Data Index: 8584591 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5668. Min Act: -0.1700
Data Index: 3315054 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.5981. Min Act: -0.1700
Data Index: 3468454 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.4418. Min Act: -0.1700
Data Index: 3520180 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.4418. Min Act: -0.1700
Data Index: 4134985 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.3793. Min Act: -0.1700
Data Index: 6074862 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.3793. Min Act: -0.1700
Data Index: 6284494 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.3481. Min Act: -0.1700
Data Index: 3037297 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.3481. Min Act: -0.1700
Data Index: 6205711 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.3168. Min Act: -0.1700
Data Index: 178047 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.2543. Min Act: -0.1700
Data Index: 3972788 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.2856. Min Act: -0.1700
Data Index: 6217562 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.2856. Min Act: -0.1700
Data Index: 1490149 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.2856. Min Act: -0.1700
Data Index: 4467711 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6199689 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1606. Min Act: -0.1700
Data Index: 1582563 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1606. Min Act: -0.1700
Data Index: 2139566 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1606. Min Act: -0.1700
Data Index: 141222 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7543. Min Range: -6.7543
Max Act: 6.1606. Min Act: -0.1700
Data Index: 7702244 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19