Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5759 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.7123. Min Act: -0.1700
Data Index: 8075882 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.6810. Min Act: -0.1700
Data Index: 6840626 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.6810. Min Act: -0.1700
Data Index: 2636341 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.6498. Min Act: -0.1700
Data Index: 4679309 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.6185. Min Act: -0.1700
Data Index: 6966917 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.5560. Min Act: -0.1700
Data Index: 7097112 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.5560. Min Act: -0.1700
Data Index: 2029437 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.5560. Min Act: -0.1700
Data Index: 3434084 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.4935. Min Act: -0.1700
Data Index: 7213896 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.5248. Min Act: -0.1700
Data Index: 5772110 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.4935. Min Act: -0.1700
Data Index: 6379034 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3998. Min Act: -0.1700
Data Index: 1135562 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3998. Min Act: -0.1700
Data Index: 1135563 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3685. Min Act: -0.1700
Data Index: 395089 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3373. Min Act: -0.1700
Data Index: 2659842 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3373. Min Act: -0.1700
Data Index: 7923442 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3373. Min Act: -0.1700
Data Index: 3747111 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3373. Min Act: -0.1700
Data Index: 7097113 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3060. Min Act: -0.1700
Data Index: 628361 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7123. Min Range: -6.7123
Max Act: 6.3060. Min Act: -0.1700
Data Index: 3345344 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19