Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.6690. Min Act: -0.1700
Data Index: 7287265 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.2939. Min Act: -0.1700
Data Index: 4710944 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.1689. Min Act: -0.1700
Data Index: 7076714 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.1064. Min Act: -0.1700
Data Index: 7285351 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.1377. Min Act: -0.1700
Data Index: 132355 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.1064. Min Act: -0.1700
Data Index: 922854 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.0439. Min Act: -0.1700
Data Index: 1386067 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6690. Min Range: -4.6690
Max Act: 4.0126. Min Act: -0.1700
Data Index: 4428251 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9501. Min Act: -0.1700
Data Index: 7376321 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9814. Min Act: -0.1700
Data Index: 1328449 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9501. Min Act: -0.1700
Data Index: 6965109 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9345. Min Act: -0.1700
Data Index: 4391629 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9345. Min Act: -0.1700
Data Index: 5820326 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9189. Min Act: -0.1700
Data Index: 7840528 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9345. Min Act: -0.1700
Data Index: 5594446 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9032. Min Act: -0.1700
Data Index: 3237569 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.8876. Min Act: -0.1700
Data Index: 1412002 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9032. Min Act: -0.1700
Data Index: 7162588 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.9032. Min Act: -0.1700
Data Index: 5566866 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6690. Min Range: -4.6690
Max Act: 3.8876. Min Act: -0.1700
Data Index: 5353242 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19