Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.9119. Min Act: -0.1700
Data Index: 4901892 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.4431. Min Act: -0.1700
Data Index: 8357979 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3494. Min Act: -0.1700
Data Index: 3962980 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3181. Min Act: -0.1700
Data Index: 523796 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5699731 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5901011 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3806. Min Act: -0.1700
Data Index: 4423408 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3181. Min Act: -0.1700
Data Index: 4424879 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.2244. Min Act: -0.1700
Data Index: 271431 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3181. Min Act: -0.1700
Data Index: 3952565 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5640204 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3494. Min Act: -0.1700
Data Index: 2162966 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3181. Min Act: -0.1700
Data Index: 1988521 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.2869. Min Act: -0.1700
Data Index: 3947758 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.2869. Min Act: -0.1700
Data Index: 2932643 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.2556. Min Act: -0.1700
Data Index: 2836203 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.2869. Min Act: -0.1700
Data Index: 7206478 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.3181. Min Act: -0.1700
Data Index: 6968032 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.2556. Min Act: -0.1700
Data Index: 1982868 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.2869. Min Act: -0.1700
Data Index: 4158229 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19