Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2455 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.7251. Min Act: -0.1700
Data Index: 7210443 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.7571. Min Act: -0.1700
Data Index: 6157391 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.7251. Min Act: -0.1700
Data Index: 4750320 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6771. Min Act: -0.1700
Data Index: 1352064 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6451. Min Act: -0.1700
Data Index: 1475172 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6611. Min Act: -0.1700
Data Index: 3153118 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6611. Min Act: -0.1700
Data Index: 5358518 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6611. Min Act: -0.1700
Data Index: 5334466 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6451. Min Act: -0.1700
Data Index: 2625800 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6611. Min Act: -0.1700
Data Index: 2494871 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6611. Min Act: -0.1700
Data Index: 810016 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6451. Min Act: -0.1700
Data Index: 8122869 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6451. Min Act: -0.1700
Data Index: 7989958 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6611. Min Act: -0.1700
Data Index: 78482 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6451. Min Act: -0.1700
Data Index: 3982372 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6611. Min Act: -0.1700
Data Index: 7973947 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6290. Min Act: -0.1700
Data Index: 3736377 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6129. Min Act: -0.1700
Data Index: 1858528 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6129. Min Act: -0.1700
Data Index: 7393017 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7571. Min Range: -2.7571
Max Act: 2.6129. Min Act: -0.1700
Data Index: 915515 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19