Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3226 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.6844. Min Act: -0.1700
Data Index: 4440079 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.6219. Min Act: -0.1700
Data Index: 224401 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.5907. Min Act: -0.1700
Data Index: 4623268 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.6219. Min Act: -0.1700
Data Index: 2497205 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.5594. Min Act: -0.1700
Data Index: 93750 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.5282. Min Act: -0.1700
Data Index: 8202143 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4969. Min Act: -0.1700
Data Index: 8804511 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4969. Min Act: -0.1700
Data Index: 5497065 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4969. Min Act: -0.1700
Data Index: 2199168 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4969. Min Act: -0.1700
Data Index: 7043217 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4969. Min Act: -0.1700
Data Index: 1557228 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4657. Min Act: -0.1699
Data Index: 2150561 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4657. Min Act: -0.1700
Data Index: 157275 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4657. Min Act: -0.1700
Data Index: 1838642 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4657. Min Act: -0.1700
Data Index: 5559499 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4344. Min Act: -0.1700
Data Index: 5100368 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4032. Min Act: -0.1700
Data Index: 8146777 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.4032. Min Act: -0.1700
Data Index: 7401259 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.3719. Min Act: -0.1700
Data Index: 1557225 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6844. Min Range: -5.6844
Max Act: 5.3719. Min Act: -0.1700
Data Index: 8574208 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19