Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1393 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.2495. Min Act: -0.1700
Data Index: 6258504 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.2183. Min Act: -0.1700
Data Index: 5824883 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.1558. Min Act: -0.1700
Data Index: 1912983 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.1558. Min Act: -0.1700
Data Index: 366436 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.1558. Min Act: -0.1700
Data Index: 451901 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0933. Min Act: -0.1700
Data Index: 2642668 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0933. Min Act: -0.1700
Data Index: 6258502 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0933. Min Act: -0.1700
Data Index: 614959 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0620. Min Act: -0.1700
Data Index: 1065320 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0620. Min Act: -0.1700
Data Index: 1294405 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0933. Min Act: -0.1700
Data Index: 8361122 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0308. Min Act: -0.1700
Data Index: 8614051 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0620. Min Act: -0.1700
Data Index: 470656 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0308. Min Act: -0.1700
Data Index: 8702604 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0620. Min Act: -0.1700
Data Index: 8354377 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2495. Min Range: -6.2495
Max Act: 6.0308. Min Act: -0.1700
Data Index: 7732657 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2495. Min Range: -6.2495
Max Act: 5.9995. Min Act: -0.1700
Data Index: 2329120 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2495. Min Range: -6.2495
Max Act: 5.9995. Min Act: -0.1700
Data Index: 2742435 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2495. Min Range: -6.2495
Max Act: 5.9995. Min Act: -0.1700
Data Index: 2276959 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2495. Min Range: -6.2495
Max Act: 5.9370. Min Act: -0.1700
Data Index: 1916458 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19