Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1398 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.2824. Min Act: -0.1700
Data Index: 7498164 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.2824. Min Act: -0.1700
Data Index: 7770984 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.2511. Min Act: -0.1700
Data Index: 1933380 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.2199. Min Act: -0.1700
Data Index: 3414080 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1886. Min Act: -0.1700
Data Index: 5314227 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1574. Min Act: -0.1700
Data Index: 8531051 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1574. Min Act: -0.1700
Data Index: 2479235 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1261. Min Act: -0.1700
Data Index: 7739297 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.1261. Min Act: -0.1700
Data Index: 7820603 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0949. Min Act: -0.1700
Data Index: 1642249 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0949. Min Act: -0.1700
Data Index: 8808408 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0636. Min Act: -0.1700
Data Index: 8720425 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0949. Min Act: -0.1700
Data Index: 1745970 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0949. Min Act: -0.1700
Data Index: 1034911 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0636. Min Act: -0.1700
Data Index: 6915336 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0636. Min Act: -0.1700
Data Index: 8722374 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0011. Min Act: -0.1700
Data Index: 256656 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0324. Min Act: -0.1700
Data Index: 4471877 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0324. Min Act: -0.1700
Data Index: 456614 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2824. Min Range: -5.2824
Max Act: 5.0324. Min Act: -0.1700
Data Index: 1407510 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19