Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 825 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0641. Min Range: -6.0641
Max Act: 6.0641. Min Act: -0.1700
Data Index: 4498480 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.9391. Min Act: -0.1700
Data Index: 7991030 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.8766. Min Act: -0.1700
Data Index: 2441574 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.8453. Min Act: -0.1700
Data Index: 5357993 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.8453. Min Act: -0.1700
Data Index: 1968923 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.8141. Min Act: -0.1700
Data Index: 6401858 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7828. Min Act: -0.1700
Data Index: 2443510 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7828. Min Act: -0.1700
Data Index: 1610322 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7516. Min Act: -0.1700
Data Index: 6414730 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7516. Min Act: -0.1700
Data Index: 5586378 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7828. Min Act: -0.1700
Data Index: 3663112 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7516. Min Act: -0.1700
Data Index: 7252674 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7203. Min Act: -0.1700
Data Index: 6263632 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7828. Min Act: -0.1700
Data Index: 4345996 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7516. Min Act: -0.1700
Data Index: 6383850 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7203. Min Act: -0.1700
Data Index: 3444777 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7203. Min Act: -0.1700
Data Index: 372245 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7203. Min Act: -0.1700
Data Index: 7057469 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7203. Min Act: -0.1700
Data Index: 4851889 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0641. Min Range: -6.0641
Max Act: 5.7203. Min Act: -0.1700
Data Index: 7687771 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19