Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0578. Min Range: -7.0578
Max Act: 7.0578. Min Act: -0.1700
Data Index: 1557580 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.9328. Min Act: -0.1700
Data Index: 529651 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.6516. Min Act: -0.1700
Data Index: 7438414 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.6203. Min Act: -0.1700
Data Index: 1599015 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.5891. Min Act: -0.1700
Data Index: 8417221 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.5578. Min Act: -0.1700
Data Index: 1395181 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.5266. Min Act: -0.1700
Data Index: 707804 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.5266. Min Act: -0.1700
Data Index: 1769145 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.3703. Min Act: -0.1700
Data Index: 8237132 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.3391. Min Act: -0.1700
Data Index: 8634439 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.3391. Min Act: -0.1700
Data Index: 1252067 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.3391. Min Act: -0.1700
Data Index: 3431871 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.3391. Min Act: -0.1700
Data Index: 5795134 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.3078. Min Act: -0.1700
Data Index: 3749947 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.3078. Min Act: -0.1700
Data Index: 3095116 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.2766. Min Act: -0.1700
Data Index: 691570 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.2766. Min Act: -0.1700
Data Index: 8175700 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.2766. Min Act: -0.1700
Data Index: 4987486 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.2141. Min Act: -0.1700
Data Index: 6768480 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0578. Min Range: -7.0578
Max Act: 6.2453. Min Act: -0.1700
Data Index: 2655753 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19