Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2380 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.7122. Min Act: -0.1700
Data Index: 319847 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.6339. Min Act: -0.1700
Data Index: 7019730 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5557. Min Act: -0.1700
Data Index: 6682679 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5087. Min Act: -0.1700
Data Index: 1119672 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5557. Min Act: -0.1700
Data Index: 5629564 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.5400. Min Act: -0.1700
Data Index: 4351383 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4617. Min Act: -0.1700
Data Index: 4357631 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4774. Min Act: -0.1700
Data Index: 4772265 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4460. Min Act: -0.1700
Data Index: 2710706 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4304. Min Act: -0.1700
Data Index: 4259095 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4460. Min Act: -0.1700
Data Index: 6331685 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4147. Min Act: -0.1700
Data Index: 2596448 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.4147. Min Act: -0.1700
Data Index: 7482535 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3833. Min Act: -0.1700
Data Index: 6507917 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3990. Min Act: -0.1700
Data Index: 4252637 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3990. Min Act: -0.1700
Data Index: 8529761 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3520. Min Act: -0.1700
Data Index: 7819513 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3833. Min Act: -0.1700
Data Index: 8803321 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3833. Min Act: -0.1700
Data Index: 1703193 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7122. Min Range: -3.7122
Max Act: 3.3676. Min Act: -0.1700
Data Index: 3075568 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19