Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 665 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3136. Min Range: -7.3136
Max Act: 7.3136. Min Act: -0.1700
Data Index: 7703869 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3136. Min Range: -7.3136
Max Act: 7.0636. Min Act: -0.1700
Data Index: 835657 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3136. Min Range: -7.3136
Max Act: 7.0011. Min Act: -0.1700
Data Index: 1905779 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.9386. Min Act: -0.1700
Data Index: 6329244 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.9386. Min Act: -0.1700
Data Index: 3127870 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.8761. Min Act: -0.1700
Data Index: 733011 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.8448. Min Act: -0.1700
Data Index: 4899267 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.8448. Min Act: -0.1700
Data Index: 7769240 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.7198. Min Act: -0.1700
Data Index: 178808 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5948. Min Act: -0.1700
Data Index: 5037132 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.6261. Min Act: -0.1700
Data Index: 4110180 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5636. Min Act: -0.1700
Data Index: 3715125 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5636. Min Act: -0.1700
Data Index: 8255883 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5323. Min Act: -0.1700
Data Index: 4418574 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5323. Min Act: -0.1700
Data Index: 4659897 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5011. Min Act: -0.1700
Data Index: 4662354 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5011. Min Act: -0.1700
Data Index: 1393040 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5323. Min Act: -0.1700
Data Index: 5649886 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.5011. Min Act: -0.1700
Data Index: 757263 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3136. Min Range: -7.3136
Max Act: 6.4698. Min Act: -0.1700
Data Index: 8052074 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19