Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1387. Min Range: -7.1387
Max Act: 7.1387. Min Act: -0.1700
Data Index: 5834400 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.9825. Min Act: -0.1700
Data Index: 6049705 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.8575. Min Act: -0.1700
Data Index: 8230459 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.7950. Min Act: -0.1700
Data Index: 6726531 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.7637. Min Act: -0.1700
Data Index: 7410417 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.7637. Min Act: -0.1700
Data Index: 3089025 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.7325. Min Act: -0.1700
Data Index: 3886904 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.7325. Min Act: -0.1700
Data Index: 6173778 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.7325. Min Act: -0.1700
Data Index: 8318491 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.7012. Min Act: -0.1700
Data Index: 5161941 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.6075. Min Act: -0.1700
Data Index: 7214452 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.5450. Min Act: -0.1700
Data Index: 1619139 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.5762. Min Act: -0.1700
Data Index: 7410410 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.5137. Min Act: -0.1700
Data Index: 774361 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.5450. Min Act: -0.1700
Data Index: 4260209 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.5450. Min Act: -0.1700
Data Index: 7588819 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.4825. Min Act: -0.1700
Data Index: 1300889 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.4825. Min Act: -0.1700
Data Index: 7410420 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.4512. Min Act: -0.1700
Data Index: 2015386 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1387. Min Range: -7.1387
Max Act: 6.4512. Min Act: -0.1700
Data Index: 7446520 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19