Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2315 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1228. Min Range: -6.1228
Max Act: 6.1228. Min Act: -0.1700
Data Index: 4632225 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1228. Min Range: -6.1228
Max Act: 6.0915. Min Act: -0.1700
Data Index: 978689 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1228. Min Range: -6.1228
Max Act: 6.0603. Min Act: -0.1700
Data Index: 8284465 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1228. Min Range: -6.1228
Max Act: 6.0290. Min Act: -0.1700
Data Index: 7879579 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9978. Min Act: -0.1700
Data Index: 4677385 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9978. Min Act: -0.1700
Data Index: 6159392 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9978. Min Act: -0.1700
Data Index: 5219205 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9978. Min Act: -0.1700
Data Index: 6189621 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9040. Min Act: -0.1700
Data Index: 7167846 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9665. Min Act: -0.1700
Data Index: 7010933 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9353. Min Act: -0.1700
Data Index: 554021 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9353. Min Act: -0.1700
Data Index: 6047594 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.9040. Min Act: -0.1700
Data Index: 6611863 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.8415. Min Act: -0.1700
Data Index: 8212334 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.8728. Min Act: -0.1700
Data Index: 4688855 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.8415. Min Act: -0.1700
Data Index: 350863 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.8415. Min Act: -0.1700
Data Index: 5601806 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.8415. Min Act: -0.1700
Data Index: 7911415 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.8103. Min Act: -0.1700
Data Index: 893846 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1228. Min Range: -6.1228
Max Act: 5.8415. Min Act: -0.1700
Data Index: 1917666 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19