Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2323 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4044. Min Range: -11.4044
Max Act: 11.4044. Min Act: -0.1700
Data Index: 107797 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4044. Min Range: -11.4044
Max Act: 11.4044. Min Act: -0.1700
Data Index: 2051487 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4044. Min Range: -11.4044
Max Act: 10.2169. Min Act: -0.1700
Data Index: 2457339 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.9669. Min Act: -0.1700
Data Index: 6452955 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.8419. Min Act: -0.1700
Data Index: 5847036 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.8419. Min Act: -0.1700
Data Index: 5302463 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.7794. Min Act: -0.1700
Data Index: 6390751 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.7169. Min Act: -0.1700
Data Index: 7205147 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.6544. Min Act: -0.1700
Data Index: 230172 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.5294. Min Act: -0.1700
Data Index: 7824487 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.4669. Min Act: -0.1700
Data Index: 7626512 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.4669. Min Act: -0.1700
Data Index: 4601234 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.4669. Min Act: -0.1700
Data Index: 5847034 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.4044. Min Act: -0.1700
Data Index: 5410996 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.4044. Min Act: -0.1700
Data Index: 601478 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.4044. Min Act: -0.1700
Data Index: 3529194 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.4044. Min Act: -0.1700
Data Index: 2038739 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.3419. Min Act: -0.1700
Data Index: 4477110 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.3419. Min Act: -0.1700
Data Index: 4489613 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4044. Min Range: -11.4044
Max Act: 9.3419. Min Act: -0.1700
Data Index: 5647686 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19