Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3563 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.3044. Min Act: -0.1700
Data Index: 676379 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2732. Min Act: -0.1700
Data Index: 3661548 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2419. Min Act: -0.1700
Data Index: 6539481 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.2107. Min Act: -0.1700
Data Index: 3724705 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.0857. Min Act: -0.1700
Data Index: 700004 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3044. Min Range: -5.3044
Max Act: 5.0544. Min Act: -0.1700
Data Index: 2502609 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.9919. Min Act: -0.1700
Data Index: 793567 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.9607. Min Act: -0.1700
Data Index: 3421767 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8982. Min Act: -0.1700
Data Index: 4702092 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.9294. Min Act: -0.1700
Data Index: 8047330 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8982. Min Act: -0.1700
Data Index: 7652621 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8982. Min Act: -0.1700
Data Index: 5860333 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8669. Min Act: -0.1700
Data Index: 2621624 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8357. Min Act: -0.1700
Data Index: 2558355 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8357. Min Act: -0.1700
Data Index: 749756 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8357. Min Act: -0.1700
Data Index: 5510173 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8357. Min Act: -0.1700
Data Index: 3139172 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8357. Min Act: -0.1700
Data Index: 5079374 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.8357. Min Act: -0.1700
Data Index: 2905081 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3044. Min Range: -5.3044
Max Act: 4.7732. Min Act: -0.1700
Data Index: 3992585 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19