Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0676. Min Range: -5.0676
Max Act: 5.0676. Min Act: -0.1700
Data Index: 3954357 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0676. Min Range: -5.0676
Max Act: 5.0363. Min Act: -0.1700
Data Index: 8549586 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.9113. Min Act: -0.1700
Data Index: 3421561 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.8488. Min Act: -0.1700
Data Index: 618113 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.8801. Min Act: -0.1700
Data Index: 284981 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.8488. Min Act: -0.1700
Data Index: 4678208 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.8176. Min Act: -0.1700
Data Index: 4636318 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.8176. Min Act: -0.1700
Data Index: 202259 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.8176. Min Act: -0.1700
Data Index: 2172174 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.8488. Min Act: -0.1700
Data Index: 4650367 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.7551. Min Act: -0.1700
Data Index: 7171878 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.7551. Min Act: -0.1700
Data Index: 7213638 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.7551. Min Act: -0.1700
Data Index: 5042654 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.7551. Min Act: -0.1700
Data Index: 8357236 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.7238. Min Act: -0.1700
Data Index: 2855042 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.7238. Min Act: -0.1700
Data Index: 1871991 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.6926. Min Act: -0.1700
Data Index: 5724124 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.6926. Min Act: -0.1700
Data Index: 1681471 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.6613. Min Act: -0.1700
Data Index: 257881 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0676. Min Range: -5.0676
Max Act: 4.6926. Min Act: -0.1700
Data Index: 7751448 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19