Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2982. Min Act: -0.1700
Data Index: 6275680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2357. Min Act: -0.1700
Data Index: 3044355 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2357. Min Act: -0.1700
Data Index: 6275668 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2357. Min Act: -0.1700
Data Index: 3459885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2044. Min Act: -0.1700
Data Index: 3326315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2044. Min Act: -0.1700
Data Index: 6275672 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2044. Min Act: -0.1700
Data Index: 8526053 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 2965428 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 6285269 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 1099578 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 1054494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 595947 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 3404222 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1419. Min Act: -0.1700
Data Index: 6275690 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 4367693 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1419. Min Act: -0.1700
Data Index: 2875682 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1419. Min Act: -0.1700
Data Index: 7065196 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1419. Min Act: -0.1699
Data Index: 2958152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1419. Min Act: -0.1700
Data Index: 6275671 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1419. Min Act: -0.1700
Data Index: 7941309 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19