Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.0641. Min Range: -16.0641
Max Act: 16.0641. Min Act: -0.1700
Data Index: 7864152 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.9391. Min Act: -0.1700
Data Index: 1895982 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.0641. Min Range: -16.0641
Max Act: 16.0641. Min Act: -0.1700
Data Index: 2710358 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.9391. Min Act: -0.1700
Data Index: 1831674 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.9391. Min Act: -0.1700
Data Index: 8404543 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.9391. Min Act: -0.1700
Data Index: 204496 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.9391. Min Act: -0.1700
Data Index: 2114717 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.9391. Min Act: -0.1700
Data Index: 6246189 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.9391. Min Act: -0.1700
Data Index: 1501801 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.8141. Min Act: -0.1700
Data Index: 3363536 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.8141. Min Act: -0.1700
Data Index: 7176843 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.8141. Min Act: -0.1700
Data Index: 2822847 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.8141. Min Act: -0.1700
Data Index: 7254739 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.8141. Min Act: -0.1700
Data Index: 7794592 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.8141. Min Act: -0.1700
Data Index: 4062146 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.8141. Min Act: -0.1700
Data Index: 7554898 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.7516. Min Act: -0.1700
Data Index: 7555756 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.6891. Min Act: -0.1700
Data Index: 1771656 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.7516. Min Act: -0.1700
Data Index: 8453358 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.0641. Min Range: -16.0641
Max Act: 15.7516. Min Act: -0.1700
Data Index: 2415304 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19