Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.6137. Min Act: -0.1700
Data Index: 8156336 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.6137. Min Act: -0.1700
Data Index: 2105508 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4887. Min Act: -0.1700
Data Index: 7219770 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4575. Min Act: -0.1700
Data Index: 1230889 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4887. Min Act: -0.1700
Data Index: 4786220 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4887. Min Act: -0.1700
Data Index: 1965843 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4575. Min Act: -0.1700
Data Index: 4463567 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4262. Min Act: -0.1700
Data Index: 404401 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.3950. Min Act: -0.1700
Data Index: 1422764 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4575. Min Act: -0.1700
Data Index: 7233557 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4262. Min Act: -0.1700
Data Index: 7941912 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4575. Min Act: -0.1700
Data Index: 4289580 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.3950. Min Act: -0.1700
Data Index: 5753407 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4575. Min Act: -0.1700
Data Index: 3665375 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.3950. Min Act: -0.1700
Data Index: 6033157 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4575. Min Act: -0.1700
Data Index: 2660236 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4262. Min Act: -0.1700
Data Index: 5279458 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.3637. Min Act: -0.1700
Data Index: 5832868 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.3950. Min Act: -0.1700
Data Index: 6103039 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6137. Min Range: -7.6137
Max Act: 7.4262. Min Act: -0.1700
Data Index: 1095301 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19