Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.9492. Min Act: -0.1700
Data Index: 1343315 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.8554. Min Act: -0.1700
Data Index: 3839001 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7929. Min Act: -0.1700
Data Index: 6175423 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7929. Min Act: -0.1700
Data Index: 8427323 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 1151763 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.8242. Min Act: -0.1700
Data Index: 7606700 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7929. Min Act: -0.1700
Data Index: 1786284 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7929. Min Act: -0.1700
Data Index: 121111 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7929. Min Act: -0.1700
Data Index: 1520597 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 3218782 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 2599954 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 49007 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 6590492 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 7504919 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 4627106 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 3735898 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 7636722 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 2598667 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 2577049 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9492. Min Range: -3.9492
Max Act: 3.7616. Min Act: -0.1700
Data Index: 8667085 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19