Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 160 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.6403. Min Act: -0.1700
Data Index: 1773681 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.6090. Min Act: -0.1700
Data Index: 6250202 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5777. Min Act: -0.1700
Data Index: 4579997 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5777. Min Act: -0.1700
Data Index: 4769962 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5777. Min Act: -0.1700
Data Index: 3459183 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5777. Min Act: -0.1700
Data Index: 3008860 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5777. Min Act: -0.1700
Data Index: 7776945 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5777. Min Act: -0.1700
Data Index: 7205863 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5777. Min Act: -0.1700
Data Index: 6575745 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5151. Min Act: -0.1700
Data Index: 1403746 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 3208085 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5151. Min Act: -0.1700
Data Index: 3404645 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 3516638 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 3750297 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 4087048 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 4175759 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 1769165 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 4196788 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 1998737 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6403. Min Range: -3.6403
Max Act: 3.5464. Min Act: -0.1700
Data Index: 4466539 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19