Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0930. Min Range: -7.0930
Max Act: 7.0930. Min Act: -0.1700
Data Index: 7859953 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0930. Min Range: -7.0930
Max Act: 7.0930. Min Act: -0.1700
Data Index: 8278909 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0930. Min Range: -7.0930
Max Act: 7.0305. Min Act: -0.1700
Data Index: 2574795 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.9680. Min Act: -0.1700
Data Index: 5540909 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.9367. Min Act: -0.1700
Data Index: 8208565 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.9055. Min Act: -0.1700
Data Index: 6362642 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.8430. Min Act: -0.1700
Data Index: 3527307 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.8742. Min Act: -0.1700
Data Index: 1764848 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.7492. Min Act: -0.1700
Data Index: 1557194 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.7492. Min Act: -0.1700
Data Index: 511425 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.7180. Min Act: -0.1700
Data Index: 5447011 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.7180. Min Act: -0.1700
Data Index: 4842027 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.6555. Min Act: -0.1700
Data Index: 3018037 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.6867. Min Act: -0.1700
Data Index: 7882738 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.6242. Min Act: -0.1700
Data Index: 4379244 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.6555. Min Act: -0.1700
Data Index: 4348165 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.6242. Min Act: -0.1700
Data Index: 5345579 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.5930. Min Act: -0.1700
Data Index: 2071167 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.5930. Min Act: -0.1700
Data Index: 1352095 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0930. Min Range: -7.0930
Max Act: 6.5930. Min Act: -0.1700
Data Index: 979143 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19