Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1130. Min Range: -6.1130
Max Act: 6.1130. Min Act: -0.1700
Data Index: 2748719 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1130. Min Range: -6.1130
Max Act: 6.1130. Min Act: -0.1700
Data Index: 7110084 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1130. Min Range: -6.1130
Max Act: 6.0818. Min Act: -0.1700
Data Index: 241091 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9880. Min Act: -0.1700
Data Index: 522685 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9880. Min Act: -0.1700
Data Index: 7395683 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9880. Min Act: -0.1700
Data Index: 4681652 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9880. Min Act: -0.1700
Data Index: 822945 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9880. Min Act: -0.1700
Data Index: 7923511 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9880. Min Act: -0.1700
Data Index: 2641875 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9255. Min Act: -0.1700
Data Index: 1443381 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9568. Min Act: -0.1700
Data Index: 3320737 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9255. Min Act: -0.1700
Data Index: 6182704 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9568. Min Act: -0.1700
Data Index: 6128589 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9255. Min Act: -0.1700
Data Index: 4487490 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9255. Min Act: -0.1700
Data Index: 7294570 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9255. Min Act: -0.1700
Data Index: 843647 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.9255. Min Act: -0.1700
Data Index: 3149477 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1139870 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.8630. Min Act: -0.1700
Data Index: 196075 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1130. Min Range: -6.1130
Max Act: 5.8943. Min Act: -0.1700
Data Index: 6347187 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19