Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.7617. Min Act: -0.1700
Data Index: 2209181 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.6367. Min Act: -0.1700
Data Index: 7017028 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.6055. Min Act: -0.1700
Data Index: 6770055 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.6055. Min Act: -0.1700
Data Index: 8574553 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.5742. Min Act: -0.1700
Data Index: 2599267 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.5430. Min Act: -0.1700
Data Index: 6920488 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.6055. Min Act: -0.1700
Data Index: 2134242 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.5742. Min Act: -0.1700
Data Index: 4599561 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.5430. Min Act: -0.1700
Data Index: 3434345 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.5430. Min Act: -0.1700
Data Index: 2684219 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.4805. Min Act: -0.1700
Data Index: 6920474 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.4180. Min Act: -0.1700
Data Index: 5705143 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.3867. Min Act: -0.1700
Data Index: 3434344 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.4180. Min Act: -0.1700
Data Index: 8602501 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.4180. Min Act: -0.1700
Data Index: 6123960 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.4492. Min Act: -0.1700
Data Index: 7167625 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.4180. Min Act: -0.1700
Data Index: 1287404 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.3555. Min Act: -0.1700
Data Index: 1592050 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.3867. Min Act: -0.1700
Data Index: 4229594 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7617. Min Range: -5.7617
Max Act: 5.3242. Min Act: -0.1700
Data Index: 5295345 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19