Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4463 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2865. Min Range: -8.2865
Max Act: 8.2865. Min Act: -0.1700
Data Index: 1838369 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2865. Min Range: -8.2865
Max Act: 7.2240. Min Act: -0.1700
Data Index: 1957920 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2865. Min Range: -8.2865
Max Act: 7.0365. Min Act: -0.1700
Data Index: 7244134 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2865. Min Range: -8.2865
Max Act: 7.0053. Min Act: -0.1700
Data Index: 2640067 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.9740. Min Act: -0.1700
Data Index: 2383908 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.9740. Min Act: -0.1700
Data Index: 881291 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.9428. Min Act: -0.1700
Data Index: 7942871 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.9115. Min Act: -0.1700
Data Index: 4776330 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.9428. Min Act: -0.1700
Data Index: 8556368 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.8803. Min Act: -0.1700
Data Index: 3763473 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.8803. Min Act: -0.1700
Data Index: 2609250 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.8490. Min Act: -0.1700
Data Index: 5758309 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.8178. Min Act: -0.1700
Data Index: 4912153 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.8178. Min Act: -0.1700
Data Index: 7013158 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.8178. Min Act: -0.1700
Data Index: 128233 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.7865. Min Act: -0.1700
Data Index: 4658058 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.7865. Min Act: -0.1700
Data Index: 2992323 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.7865. Min Act: -0.1700
Data Index: 5922518 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.7553. Min Act: -0.1700
Data Index: 3564798 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2865. Min Range: -8.2865
Max Act: 6.7553. Min Act: -0.1700
Data Index: 431868 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19