Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2693 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.8524. Min Act: -0.1700
Data Index: 5914093 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.7899. Min Act: -0.1700
Data Index: 2190513 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.5087. Min Act: -0.1700
Data Index: 1565989 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.4774. Min Act: -0.1700
Data Index: 4118119 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.4774. Min Act: -0.1700
Data Index: 3348273 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.4149. Min Act: -0.1700
Data Index: 1545689 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3837. Min Act: -0.1700
Data Index: 6335007 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3837. Min Act: -0.1700
Data Index: 4025038 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3837. Min Act: -0.1700
Data Index: 608856 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.4149. Min Act: -0.1700
Data Index: 1467794 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3837. Min Act: -0.1700
Data Index: 3494744 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3524. Min Act: -0.1700
Data Index: 6393332 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3524. Min Act: -0.1700
Data Index: 8521067 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3524. Min Act: -0.1700
Data Index: 104095 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3524. Min Act: -0.1700
Data Index: 2338953 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3212. Min Act: -0.1700
Data Index: 5825049 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3212. Min Act: -0.1700
Data Index: 4772486 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3524. Min Act: -0.1700
Data Index: 1264603 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3212. Min Act: -0.1700
Data Index: 708481 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8524. Min Range: -4.8524
Max Act: 4.3212. Min Act: -0.1700
Data Index: 53480 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19