Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0669. Min Act: -0.1700
Data Index: 7643041 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0356. Min Act: -0.1700
Data Index: 3732240 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0356. Min Act: -0.1700
Data Index: 4940013 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0044. Min Act: -0.1700
Data Index: 4215897 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0044. Min Act: -0.1700
Data Index: 4718138 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0044. Min Act: -0.1700
Data Index: 3013407 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9731. Min Act: -0.1700
Data Index: 3698462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0044. Min Act: -0.1700
Data Index: 7671283 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9731. Min Act: -0.1700
Data Index: 658982 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9731. Min Act: -0.1700
Data Index: 3325394 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9731. Min Act: -0.1700
Data Index: 6154466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0044. Min Act: -0.1700
Data Index: 6937544 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9731. Min Act: -0.1700
Data Index: 1791604 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9731. Min Act: -0.1700
Data Index: 2792413 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0669. Min Range: -4.0669
Max Act: 4.0044. Min Act: -0.1700
Data Index: 4335 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9418. Min Act: -0.1700
Data Index: 8057196 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9418. Min Act: -0.1700
Data Index: 2201981 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9418. Min Act: -0.1700
Data Index: 2293091 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9731. Min Act: -0.1700
Data Index: 6942666 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0669. Min Range: -4.0669
Max Act: 3.9418. Min Act: -0.1700
Data Index: 4492464 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19