Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5390 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.4951. Min Act: -0.1700
Data Index: 2706295 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.2451. Min Act: -0.1700
Data Index: 1697625 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.1514. Min Act: -0.1700
Data Index: 3440249 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.1201. Min Act: -0.1700
Data Index: 549248 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.1201. Min Act: -0.1700
Data Index: 2920634 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.1514. Min Act: -0.1700
Data Index: 5815514 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0889. Min Act: -0.1700
Data Index: 3648448 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0889. Min Act: -0.1700
Data Index: 8743573 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0889. Min Act: -0.1700
Data Index: 111139 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0576. Min Act: -0.1700
Data Index: 8202618 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0889. Min Act: -0.1700
Data Index: 3206 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0576. Min Act: -0.1700
Data Index: 8305114 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0889. Min Act: -0.1700
Data Index: 5228867 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0264. Min Act: -0.1700
Data Index: 5712738 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4951. Min Range: -7.4951
Max Act: 7.0264. Min Act: -0.1700
Data Index: 4209021 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.9951. Min Act: -0.1700
Data Index: 5576840 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.9951. Min Act: -0.1700
Data Index: 7348549 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.9639. Min Act: -0.1700
Data Index: 3436611 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.9639. Min Act: -0.1700
Data Index: 3333747 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4951. Min Range: -7.4951
Max Act: 6.9014. Min Act: -0.1700
Data Index: 1824631 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19