Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4437 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.3982. Min Act: -0.1700
Data Index: 3170223 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.3044. Min Act: -0.1700
Data Index: 3993186 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.2732. Min Act: -0.1700
Data Index: 1598745 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.2732. Min Act: -0.1700
Data Index: 7877659 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.2419. Min Act: -0.1700
Data Index: 5333881 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1482. Min Act: -0.1700
Data Index: 5226591 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1794. Min Act: -0.1700
Data Index: 3624636 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1794. Min Act: -0.1700
Data Index: 5333878 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1794. Min Act: -0.1700
Data Index: 8313685 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1794. Min Act: -0.1700
Data Index: 1418228 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1169. Min Act: -0.1700
Data Index: 466790 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1169. Min Act: -0.1700
Data Index: 8337802 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1169. Min Act: -0.1700
Data Index: 3697056 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.1482. Min Act: -0.1700
Data Index: 5333884 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.0857. Min Act: -0.1700
Data Index: 7046563 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.0857. Min Act: -0.1700
Data Index: 1632365 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.0857. Min Act: -0.1700
Data Index: 6846535 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.0857. Min Act: -0.1700
Data Index: 1250295 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.0857. Min Act: -0.1700
Data Index: 6334927 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3982. Min Range: -7.3982
Max Act: 7.0232. Min Act: -0.1700
Data Index: 670951 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19