Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5356 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.4981. Min Act: -0.1700
Data Index: 7108834 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.3731. Min Act: -0.1700
Data Index: 4728776 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.2793. Min Act: -0.1700
Data Index: 5760809 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.2793. Min Act: -0.1700
Data Index: 5510442 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.2793. Min Act: -0.1700
Data Index: 2993952 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.2168. Min Act: -0.1700
Data Index: 5542082 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.1856. Min Act: -0.1700
Data Index: 4128516 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.1856. Min Act: -0.1700
Data Index: 487051 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.1856. Min Act: -0.1700
Data Index: 5903378 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.1543. Min Act: -0.1700
Data Index: 6025115 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.1231. Min Act: -0.1700
Data Index: 6698009 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.1231. Min Act: -0.1700
Data Index: 924300 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.0918. Min Act: -0.1700
Data Index: 4678878 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.0918. Min Act: -0.1700
Data Index: 1812929 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.0606. Min Act: -0.1700
Data Index: 924161 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.0293. Min Act: -0.1700
Data Index: 4410196 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.0293. Min Act: -0.1700
Data Index: 7942170 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4981. Min Range: -7.4981
Max Act: 7.0293. Min Act: -0.1700
Data Index: 4356645 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4981. Min Range: -7.4981
Max Act: 6.9981. Min Act: -0.1700
Data Index: 3930175 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4981. Min Range: -7.4981
Max Act: 6.9981. Min Act: -0.1700
Data Index: 2275040 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19