Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.6708. Min Act: -0.1700
Data Index: 7265384 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.7021. Min Act: -0.1700
Data Index: 8198707 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.6708. Min Act: -0.1700
Data Index: 5591983 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.6708. Min Act: -0.1700
Data Index: 7265389 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.6396. Min Act: -0.1700
Data Index: 8198732 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.5771. Min Act: -0.1700
Data Index: 1660261 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.5458. Min Act: -0.1700
Data Index: 1359100 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 2999751 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 4394904 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 1168281 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 4392010 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4521. Min Act: -0.1700
Data Index: 6988159 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4833. Min Act: -0.1700
Data Index: 6056956 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.5146. Min Act: -0.1700
Data Index: 795975 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4521. Min Act: -0.1700
Data Index: 948392 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4833. Min Act: -0.1700
Data Index: 6168957 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4208. Min Act: -0.1700
Data Index: 1154418 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4521. Min Act: -0.1700
Data Index: 4669221 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4208. Min Act: -0.1700
Data Index: 1182817 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7021. Min Range: -5.7021
Max Act: 5.4208. Min Act: -0.1700
Data Index: 3086872 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19