Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3753 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0102. Min Range: -4.0102
Max Act: 4.0102. Min Act: -0.1700
Data Index: 1091513 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.9477. Min Act: -0.1700
Data Index: 3973083 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8851. Min Act: -0.1700
Data Index: 4586919 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8226. Min Act: -0.1700
Data Index: 2130770 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8070. Min Act: -0.1700
Data Index: 312605 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8070. Min Act: -0.1700
Data Index: 4210032 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 6209971 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 8425187 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.8070. Min Act: -0.1700
Data Index: 8112555 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 5666258 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7913. Min Act: -0.1700
Data Index: 8643892 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7600. Min Act: -0.1700
Data Index: 1018870 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7600. Min Act: -0.1700
Data Index: 7391202 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7600. Min Act: -0.1700
Data Index: 2895664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7600. Min Act: -0.1700
Data Index: 4434114 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7600. Min Act: -0.1700
Data Index: 2934451 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7444. Min Act: -0.1700
Data Index: 4957735 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7444. Min Act: -0.1700
Data Index: 3324780 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7444. Min Act: -0.1700
Data Index: 4375168 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0102. Min Range: -4.0102
Max Act: 3.7444. Min Act: -0.1700
Data Index: 3446007 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19