Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8881. Min Act: -0.1700
Data Index: 4498167 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8624. Min Act: -0.1693
Data Index: 2728402 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8282. Min Act: -0.1700
Data Index: 7082691 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8282. Min Act: -0.1700
Data Index: 7259357 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8282. Min Act: -0.1700
Data Index: 5275141 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8282. Min Act: -0.1675
Data Index: 7082689 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8282. Min Act: -0.1685
Data Index: 4269238 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8196. Min Act: -0.1700
Data Index: 7746366 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8024. Min Act: -0.1700
Data Index: 2928514 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8024. Min Act: -0.1700
Data Index: 7270534 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.7938. Min Act: -0.1698
Data Index: 4413102 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8024. Min Act: -0.1700
Data Index: 2467471 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8024. Min Act: -0.1700
Data Index: 5782119 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.7938. Min Act: -0.1699
Data Index: 4693685 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.7938. Min Act: -0.1700
Data Index: 5454872 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.8024. Min Act: -0.1700
Data Index: 8150738 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.7852. Min Act: -0.1700
Data Index: 6266656 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.7852. Min Act: -0.1699
Data Index: 6493488 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.7852. Min Act: -0.1669
Data Index: 274699 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8881. Min Range: -1.8881
Max Act: 1.7852. Min Act: -0.1694
Data Index: 2624043 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19