Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.7554. Min Act: -0.1700
Data Index: 6201704 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.6303. Min Act: -0.1700
Data Index: 1727934 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5677. Min Act: -0.1700
Data Index: 7907386 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5677. Min Act: -0.1700
Data Index: 2061564 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5677. Min Act: -0.1700
Data Index: 8003693 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5677. Min Act: -0.1700
Data Index: 4463891 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5364. Min Act: -0.1700
Data Index: 7095541 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5677. Min Act: -0.1700
Data Index: 181378 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5364. Min Act: -0.1700
Data Index: 8692600 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5364. Min Act: -0.1700
Data Index: 6329723 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5050. Min Act: -0.1700
Data Index: 3886732 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5050. Min Act: -0.1700
Data Index: 2007453 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5050. Min Act: -0.1700
Data Index: 5294832 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5050. Min Act: -0.1700
Data Index: 4223024 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.4737. Min Act: -0.1700
Data Index: 3624534 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.4737. Min Act: -0.1700
Data Index: 7717725 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5050. Min Act: -0.1700
Data Index: 1471818 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.4737. Min Act: -0.1700
Data Index: 3659465 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.4737. Min Act: -0.1700
Data Index: 6415021 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7554. Min Range: -3.7554
Max Act: 3.5050. Min Act: -0.1700
Data Index: 6851599 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19