Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.3404. Min Act: -0.1700
Data Index: 8522964 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.3404. Min Act: -0.1700
Data Index: 1502788 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.3090. Min Act: -0.1700
Data Index: 4277694 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.2776. Min Act: -0.1700
Data Index: 5419551 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.2462. Min Act: -0.1700
Data Index: 6380284 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1990. Min Act: -0.1700
Data Index: 3394925 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1833. Min Act: -0.1700
Data Index: 7820261 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1990. Min Act: -0.1700
Data Index: 6759022 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1833. Min Act: -0.1700
Data Index: 523244 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1833. Min Act: -0.1700
Data Index: 4056370 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1676. Min Act: -0.1700
Data Index: 5227975 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1990. Min Act: -0.1700
Data Index: 8653397 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1518. Min Act: -0.1700
Data Index: 1984068 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1833. Min Act: -0.1700
Data Index: 2920727 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1676. Min Act: -0.1700
Data Index: 8404567 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1676. Min Act: -0.1700
Data Index: 767857 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1203. Min Act: -0.1700
Data Index: 3709978 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1361. Min Act: -0.1700
Data Index: 7628925 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1361. Min Act: -0.1700
Data Index: 7565893 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3404. Min Range: -3.3404
Max Act: 3.1046. Min Act: -0.1700
Data Index: 4210653 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19