Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0563. Min Range: -5.0563
Max Act: 5.0563. Min Act: -0.1700
Data Index: 5390349 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.9625. Min Act: -0.1700
Data Index: 1832592 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.9625. Min Act: -0.1700
Data Index: 3973202 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.9313. Min Act: -0.1700
Data Index: 1356205 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8375. Min Act: -0.1700
Data Index: 5920872 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8688. Min Act: -0.1700
Data Index: 5333637 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8688. Min Act: -0.1700
Data Index: 1008589 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8063. Min Act: -0.1700
Data Index: 652813 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8063. Min Act: -0.1700
Data Index: 6465781 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8063. Min Act: -0.1700
Data Index: 4162740 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8063. Min Act: -0.1700
Data Index: 1315338 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.8063. Min Act: -0.1700
Data Index: 1405790 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7750. Min Act: -0.1700
Data Index: 5265254 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7750. Min Act: -0.1700
Data Index: 7727724 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7438. Min Act: -0.1700
Data Index: 2322207 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7750. Min Act: -0.1700
Data Index: 383627 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7438. Min Act: -0.1700
Data Index: 5712761 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7438. Min Act: -0.1700
Data Index: 5858199 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7438. Min Act: -0.1700
Data Index: 7223396 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0563. Min Range: -5.0563
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6553107 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19