Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.8163. Min Act: -0.1700
Data Index: 4994923 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.7366. Min Act: -0.1700
Data Index: 7181237 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.7366. Min Act: -0.1700
Data Index: 1626723 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.7206. Min Act: -0.1700
Data Index: 4219200 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6886. Min Act: -0.1700
Data Index: 6828999 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6405. Min Act: -0.1700
Data Index: 2840528 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6405. Min Act: -0.1700
Data Index: 7065303 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5923. Min Act: -0.1700
Data Index: 4024967 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.6084. Min Act: -0.1700
Data Index: 8781844 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5923. Min Act: -0.1700
Data Index: 3688328 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5923. Min Act: -0.1700
Data Index: 7192047 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5762. Min Act: -0.1700
Data Index: 4825789 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5762. Min Act: -0.1700
Data Index: 5168249 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5601. Min Act: -0.1700
Data Index: 4038820 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5439. Min Act: -0.1700
Data Index: 4715333 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5278. Min Act: -0.1700
Data Index: 599145 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5439. Min Act: -0.1700
Data Index: 4351996 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5278. Min Act: -0.1700
Data Index: 5352612 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5278. Min Act: -0.1700
Data Index: 1225938 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8163. Min Range: -2.8163
Max Act: 2.5278. Min Act: -0.1700
Data Index: 5468134 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19