Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1600 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.9420. Min Act: -0.1700
Data Index: 35843 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.9103. Min Act: -0.1700
Data Index: 8019706 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.8468. Min Act: -0.1700
Data Index: 1602771 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.8309. Min Act: -0.1700
Data Index: 3698378 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7831. Min Act: -0.1700
Data Index: 2028319 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7353. Min Act: -0.1700
Data Index: 1744415 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7353. Min Act: -0.1700
Data Index: 7168767 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7672. Min Act: -0.1700
Data Index: 2128538 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7033. Min Act: -0.1700
Data Index: 2000176 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7512. Min Act: -0.1700
Data Index: 27892 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7193. Min Act: -0.1700
Data Index: 3464944 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7353. Min Act: -0.1700
Data Index: 3655795 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7193. Min Act: -0.1700
Data Index: 4075664 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7193. Min Act: -0.1700
Data Index: 6809686 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7033. Min Act: -0.1700
Data Index: 2428010 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7033. Min Act: -0.1700
Data Index: 6495683 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7033. Min Act: -0.1700
Data Index: 3274309 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.7033. Min Act: -0.1700
Data Index: 113153 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.6873. Min Act: -0.1700
Data Index: 8305009 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9420. Min Range: -2.9420
Max Act: 2.6713. Min Act: -0.1700
Data Index: 887061 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19