Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4327. Min Range: -6.4327
Max Act: 6.4327. Min Act: -0.1700
Data Index: 4255180 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4327. Min Range: -6.4327
Max Act: 6.3702. Min Act: -0.1700
Data Index: 7647845 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4327. Min Range: -6.4327
Max Act: 6.1514. Min Act: -0.1700
Data Index: 3202821 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4327. Min Range: -6.4327
Max Act: 6.0577. Min Act: -0.1700
Data Index: 8799321 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4327. Min Range: -6.4327
Max Act: 6.0264. Min Act: -0.1700
Data Index: 3459836 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4327. Min Range: -6.4327
Max Act: 6.0264. Min Act: -0.1700
Data Index: 1890059 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.9952. Min Act: -0.1700
Data Index: 7526470 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.9639. Min Act: -0.1700
Data Index: 6769015 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.9639. Min Act: -0.1700
Data Index: 4447557 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.9327. Min Act: -0.1700
Data Index: 7973914 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.9327. Min Act: -0.1700
Data Index: 1675754 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.8702. Min Act: -0.1700
Data Index: 6538163 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.8702. Min Act: -0.1700
Data Index: 7610959 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.8389. Min Act: -0.1700
Data Index: 7017090 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.8389. Min Act: -0.1700
Data Index: 6735776 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.8389. Min Act: -0.1700
Data Index: 4002601 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.8077. Min Act: -0.1700
Data Index: 7091182 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.7764. Min Act: -0.1700
Data Index: 7201874 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.7764. Min Act: -0.1700
Data Index: 4729096 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4327. Min Range: -6.4327
Max Act: 5.7764. Min Act: -0.1700
Data Index: 4272045 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19