Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0357. Min Range: -5.0357
Max Act: 5.0357. Min Act: -0.1700
Data Index: 8470344 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.9732. Min Act: -0.1700
Data Index: 3650968 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.9732. Min Act: -0.1700
Data Index: 424288 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.9732. Min Act: -0.1700
Data Index: 6659153 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.9420. Min Act: -0.1700
Data Index: 6621812 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.9107. Min Act: -0.1700
Data Index: 891238 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.9107. Min Act: -0.1700
Data Index: 4100409 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8482. Min Act: -0.1700
Data Index: 1919657 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8795. Min Act: -0.1700
Data Index: 639609 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.9107. Min Act: -0.1700
Data Index: 4120089 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8170. Min Act: -0.1700
Data Index: 2426290 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8482. Min Act: -0.1700
Data Index: 4449533 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8482. Min Act: -0.1700
Data Index: 2344506 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8482. Min Act: -0.1700
Data Index: 2023819 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8170. Min Act: -0.1700
Data Index: 4290093 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.8170. Min Act: -0.1700
Data Index: 441705 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.7857. Min Act: -0.1700
Data Index: 6760431 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.7857. Min Act: -0.1700
Data Index: 2594550 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.7857. Min Act: -0.1700
Data Index: 6338663 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0357. Min Range: -5.0357
Max Act: 4.7857. Min Act: -0.1700
Data Index: 3132028 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19