Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2909 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4668. Min Range: -6.4668
Max Act: 6.4668. Min Act: -0.1700
Data Index: 2163618 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4668. Min Range: -6.4668
Max Act: 6.4043. Min Act: -0.1700
Data Index: 2725507 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4668. Min Range: -6.4668
Max Act: 6.3731. Min Act: -0.1700
Data Index: 8692647 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4668. Min Range: -6.4668
Max Act: 6.0606. Min Act: -0.1700
Data Index: 4499999 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.9668. Min Act: -0.1700
Data Index: 6060803 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.9356. Min Act: -0.1700
Data Index: 2012555 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.9043. Min Act: -0.1700
Data Index: 3093094 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.9043. Min Act: -0.1700
Data Index: 2718233 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8731. Min Act: -0.1700
Data Index: 2725504 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8731. Min Act: -0.1700
Data Index: 5232305 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8418. Min Act: -0.1700
Data Index: 2120966 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8418. Min Act: -0.1700
Data Index: 8692648 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8418. Min Act: -0.1700
Data Index: 6016641 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8418. Min Act: -0.1700
Data Index: 1882700 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8106. Min Act: -0.1700
Data Index: 8202809 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.8106. Min Act: -0.1700
Data Index: 2673270 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 5163327 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 4069937 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.7793. Min Act: -0.1700
Data Index: 1677023 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4668. Min Range: -6.4668
Max Act: 5.7481. Min Act: -0.1700
Data Index: 7168245 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19