Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3914 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.6425. Min Act: -0.1700
Data Index: 550709 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.6112. Min Act: -0.1700
Data Index: 604710 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.6112. Min Act: -0.1700
Data Index: 1709047 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.6112. Min Act: -0.1700
Data Index: 3284101 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.5487. Min Act: -0.1700
Data Index: 8728090 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.5487. Min Act: -0.1700
Data Index: 97827 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.5175. Min Act: -0.1700
Data Index: 4671704 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.5175. Min Act: -0.1700
Data Index: 5457795 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4862. Min Act: -0.1700
Data Index: 1336193 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4862. Min Act: -0.1700
Data Index: 8040797 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4862. Min Act: -0.1700
Data Index: 4794632 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4862. Min Act: -0.1700
Data Index: 6189637 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4550. Min Act: -0.1700
Data Index: 6593833 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4862. Min Act: -0.1700
Data Index: 7477531 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4550. Min Act: -0.1700
Data Index: 3285832 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4550. Min Act: -0.1700
Data Index: 4325689 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4237. Min Act: -0.1700
Data Index: 1094152 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4237. Min Act: -0.1700
Data Index: 7499175 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4237. Min Act: -0.1700
Data Index: 3771488 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6425. Min Range: -5.6425
Max Act: 5.4237. Min Act: -0.1700
Data Index: 3012839 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19