Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4777 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.7549. Min Act: -0.1700
Data Index: 6769305 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.3799. Min Act: -0.1700
Data Index: 97749 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.3486. Min Act: -0.1700
Data Index: 782087 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.3174. Min Act: -0.1700
Data Index: 1048962 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.2549. Min Act: -0.1700
Data Index: 4418980 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.2236. Min Act: -0.1700
Data Index: 5316997 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.2236. Min Act: -0.1700
Data Index: 4846611 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.1924. Min Act: -0.1700
Data Index: 5462470 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.1611. Min Act: -0.1700
Data Index: 678235 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.1611. Min Act: -0.1700
Data Index: 4656888 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.1299. Min Act: -0.1700
Data Index: 1928987 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.1299. Min Act: -0.1700
Data Index: 4622156 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0986. Min Act: -0.1700
Data Index: 7167526 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0674. Min Act: -0.1700
Data Index: 4585950 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0986. Min Act: -0.1700
Data Index: 2579785 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0674. Min Act: -0.1700
Data Index: 3855193 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0986. Min Act: -0.1700
Data Index: 1759851 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0361. Min Act: -0.1700
Data Index: 4674298 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0361. Min Act: -0.1700
Data Index: 366873 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7549. Min Range: -6.7549
Max Act: 6.0049. Min Act: -0.1700
Data Index: 4668631 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19