Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1202. Min Range: -6.1202
Max Act: 6.1202. Min Act: -0.1700
Data Index: 8167700 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1202. Min Range: -6.1202
Max Act: 6.0577. Min Act: -0.1700
Data Index: 439938 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1202. Min Range: -6.1202
Max Act: 6.0265. Min Act: -0.1700
Data Index: 4972610 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1202. Min Range: -6.1202
Max Act: 6.0577. Min Act: -0.1700
Data Index: 7265304 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1202. Min Range: -6.1202
Max Act: 6.0265. Min Act: -0.1700
Data Index: 1651204 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1202. Min Range: -6.1202
Max Act: 6.0265. Min Act: -0.1700
Data Index: 4458731 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9952. Min Act: -0.1700
Data Index: 3576343 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9952. Min Act: -0.1700
Data Index: 1134462 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9640. Min Act: -0.1700
Data Index: 2495 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9952. Min Act: -0.1700
Data Index: 2936899 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9327. Min Act: -0.1700
Data Index: 7571940 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9640. Min Act: -0.1700
Data Index: 7566854 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9015. Min Act: -0.1700
Data Index: 3610486 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9015. Min Act: -0.1700
Data Index: 36353 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.8702. Min Act: -0.1700
Data Index: 1193466 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.8702. Min Act: -0.1700
Data Index: 2193011 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.8390. Min Act: -0.1700
Data Index: 2489464 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.8702. Min Act: -0.1700
Data Index: 6993707 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.9015. Min Act: -0.1700
Data Index: 1260004 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1202. Min Range: -6.1202
Max Act: 5.8702. Min Act: -0.1700
Data Index: 295093 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19