Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 470 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.2764. Min Act: -0.1700
Data Index: 5563249 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.1514. Min Act: -0.1700
Data Index: 7346569 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.1202. Min Act: -0.1700
Data Index: 91826 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.1202. Min Act: -0.1700
Data Index: 6217125 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.0889. Min Act: -0.1700
Data Index: 8605020 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.0577. Min Act: -0.1700
Data Index: 4367592 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.0577. Min Act: -0.1700
Data Index: 3973233 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9951. Min Act: -0.1700
Data Index: 878044 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.0264. Min Act: -0.1700
Data Index: 5458486 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2764. Min Range: -4.2764
Max Act: 4.0264. Min Act: -0.1700
Data Index: 6862310 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9951. Min Act: -0.1700
Data Index: 2415683 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9326. Min Act: -0.1700
Data Index: 8568275 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9639. Min Act: -0.1700
Data Index: 1882305 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9639. Min Act: -0.1700
Data Index: 7088553 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9639. Min Act: -0.1700
Data Index: 6714138 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9639. Min Act: -0.1700
Data Index: 8584241 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9326. Min Act: -0.1700
Data Index: 3306034 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9326. Min Act: -0.1700
Data Index: 3405182 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9326. Min Act: -0.1700
Data Index: 4007825 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2764. Min Range: -4.2764
Max Act: 3.9326. Min Act: -0.1700
Data Index: 6786866 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19