Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.8849. Min Act: -0.1700
Data Index: 2314593 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.8213. Min Act: -0.1700
Data Index: 2437158 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7416. Min Act: -0.1700
Data Index: 2642749 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7416. Min Act: -0.1700
Data Index: 8103368 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7416. Min Act: -0.1700
Data Index: 317841 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7416. Min Act: -0.1700
Data Index: 1076354 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7256. Min Act: -0.1700
Data Index: 7497418 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7096. Min Act: -0.1700
Data Index: 2699628 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7256. Min Act: -0.1700
Data Index: 4941336 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.7096. Min Act: -0.1700
Data Index: 6394059 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6936. Min Act: -0.1700
Data Index: 2140914 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6936. Min Act: -0.1700
Data Index: 1157434 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6776. Min Act: -0.1700
Data Index: 6016244 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6776. Min Act: -0.1700
Data Index: 4785198 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6776. Min Act: -0.1700
Data Index: 5504968 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6456. Min Act: -0.1700
Data Index: 4145194 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6616. Min Act: -0.1700
Data Index: 7538734 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6776. Min Act: -0.1700
Data Index: 5325961 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6616. Min Act: -0.1700
Data Index: 7097725 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8849. Min Range: -2.8849
Max Act: 2.6456. Min Act: -0.1700
Data Index: 1424247 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19