Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0860. Min Range: -4.0860
Max Act: 4.0860. Min Act: -0.1700
Data Index: 786858 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0860. Min Range: -4.0860
Max Act: 4.0860. Min Act: -0.1700
Data Index: 4899133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0860. Min Range: -4.0860
Max Act: 4.0860. Min Act: -0.1700
Data Index: 3379820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0860. Min Range: -4.0860
Max Act: 4.0548. Min Act: -0.1700
Data Index: 1769574 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.9923. Min Act: -0.1700
Data Index: 6198285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.9923. Min Act: -0.1700
Data Index: 3685677 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.9923. Min Act: -0.1700
Data Index: 1366887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.9610. Min Act: -0.1700
Data Index: 6435863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.9610. Min Act: -0.1700
Data Index: 1246120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.9297. Min Act: -0.1700
Data Index: 6422924 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8985. Min Act: -0.1700
Data Index: 2434165 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8985. Min Act: -0.1700
Data Index: 1311393 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8985. Min Act: -0.1700
Data Index: 7652616 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8672. Min Act: -0.1700
Data Index: 7534582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8672. Min Act: -0.1700
Data Index: 8475548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8359. Min Act: -0.1700
Data Index: 3347007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8359. Min Act: -0.1700
Data Index: 2310981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8359. Min Act: -0.1700
Data Index: 6276544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8359. Min Act: -0.1700
Data Index: 7461232 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0860. Min Range: -4.0860
Max Act: 3.8359. Min Act: -0.1700
Data Index: 1313723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19