Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.5260. Min Act: -0.1700
Data Index: 4848058 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.4947. Min Act: -0.1700
Data Index: 3781385 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.4322. Min Act: -0.1700
Data Index: 3659530 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.1510. Min Act: -0.1700
Data Index: 2745039 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.1197. Min Act: -0.1700
Data Index: 524756 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.0885. Min Act: -0.1700
Data Index: 512432 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.0885. Min Act: -0.1700
Data Index: 1258460 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9947. Min Act: -0.1700
Data Index: 3611508 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.0260. Min Act: -0.1700
Data Index: 8183380 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5260. Min Range: -7.5260
Max Act: 7.0260. Min Act: -0.1700
Data Index: 8726410 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9947. Min Act: -0.1700
Data Index: 631299 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9635. Min Act: -0.1700
Data Index: 3271897 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9322. Min Act: -0.1700
Data Index: 5637484 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9322. Min Act: -0.1700
Data Index: 6007195 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9322. Min Act: -0.1700
Data Index: 2455868 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9322. Min Act: -0.1700
Data Index: 7763047 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9635. Min Act: -0.1700
Data Index: 856574 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9322. Min Act: -0.1700
Data Index: 190016 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9010. Min Act: -0.1700
Data Index: 847161 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5260. Min Range: -7.5260
Max Act: 6.9322. Min Act: -0.1700
Data Index: 84201 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19