Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1716. Min Range: -6.1716
Max Act: 6.1716. Min Act: -0.1700
Data Index: 7096928 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1716. Min Range: -6.1716
Max Act: 6.0154. Min Act: -0.1700
Data Index: 1367478 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.7341. Min Act: -0.1700
Data Index: 1533588 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.7029. Min Act: -0.1700
Data Index: 4724724 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.6716. Min Act: -0.1700
Data Index: 4495478 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.5779. Min Act: -0.1700
Data Index: 2436854 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.4841. Min Act: -0.1700
Data Index: 7613424 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.4841. Min Act: -0.1700
Data Index: 1446854 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.4529. Min Act: -0.1700
Data Index: 3963173 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.4216. Min Act: -0.1700
Data Index: 862676 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.3591. Min Act: -0.1700
Data Index: 3848308 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.3591. Min Act: -0.1700
Data Index: 6175233 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.3279. Min Act: -0.1700
Data Index: 2112134 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.3591. Min Act: -0.1700
Data Index: 4583468 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.3279. Min Act: -0.1700
Data Index: 3168452 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.3591. Min Act: -0.1700
Data Index: 5350596 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.3279. Min Act: -0.1700
Data Index: 768061 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.2654. Min Act: -0.1700
Data Index: 4439716 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.2966. Min Act: -0.1700
Data Index: 7539942 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1716. Min Range: -6.1716
Max Act: 5.2966. Min Act: -0.1700
Data Index: 6100070 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19