Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0404. Min Range: -5.0404
Max Act: 5.0404. Min Act: -0.1700
Data Index: 5121720 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0404. Min Range: -5.0404
Max Act: 5.0091. Min Act: -0.1700
Data Index: 3902229 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0404. Min Range: -5.0404
Max Act: 5.0091. Min Act: -0.1700
Data Index: 2664281 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 6124926 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9779. Min Act: -0.1700
Data Index: 1482122 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9779. Min Act: -0.1700
Data Index: 7183259 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 7987064 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9779. Min Act: -0.1700
Data Index: 3169325 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 2323189 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9154. Min Act: -0.1700
Data Index: 2847083 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9779. Min Act: -0.1700
Data Index: 1133293 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 2607983 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 4350637 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 5111454 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9154. Min Act: -0.1700
Data Index: 1253385 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 1276714 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 5878145 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9154. Min Act: -0.1700
Data Index: 4745746 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9466. Min Act: -0.1700
Data Index: 1233932 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0404. Min Range: -5.0404
Max Act: 4.9154. Min Act: -0.1700
Data Index: 331440 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19