Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4637 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7887. Min Act: -0.1700
Data Index: 1456117 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7715. Min Act: -0.1700
Data Index: 4651468 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7542. Min Act: -0.1700
Data Index: 8224235 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7887. Min Act: -0.1700
Data Index: 3636893 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7715. Min Act: -0.1700
Data Index: 39641 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7196. Min Act: -0.1700
Data Index: 5080598 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7196. Min Act: -0.1700
Data Index: 1763515 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.7023. Min Act: -0.1700
Data Index: 5904228 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6850. Min Act: -0.1700
Data Index: 4033269 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6850. Min Act: -0.1700
Data Index: 990416 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6850. Min Act: -0.1700
Data Index: 7328667 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6850. Min Act: -0.1700
Data Index: 7846478 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6850. Min Act: -0.1700
Data Index: 1923151 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6676. Min Act: -0.1700
Data Index: 8581812 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6676. Min Act: -0.1700
Data Index: 752754 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6676. Min Act: -0.1700
Data Index: 2372357 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6676. Min Act: -0.1700
Data Index: 1284683 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6502. Min Act: -0.1700
Data Index: 6239752 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6676. Min Act: -0.1700
Data Index: 5928083 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7887. Min Range: -1.7887
Max Act: 1.6502. Min Act: -0.1700
Data Index: 3277306 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19