Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.7040. Min Act: -0.1700
Data Index: 1898851 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.6101. Min Act: -0.1700
Data Index: 1686268 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.6101. Min Act: -0.1700
Data Index: 8338503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.6101. Min Act: -0.1700
Data Index: 826719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5475. Min Act: -0.1700
Data Index: 519003 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5475. Min Act: -0.1700
Data Index: 8131854 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5162. Min Act: -0.1700
Data Index: 3286700 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5162. Min Act: -0.1700
Data Index: 3936626 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5162. Min Act: -0.1700
Data Index: 3124335 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5162. Min Act: -0.1700
Data Index: 7480631 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5005. Min Act: -0.1700
Data Index: 5233108 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5005. Min Act: -0.1700
Data Index: 5460618 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5005. Min Act: -0.1700
Data Index: 1755200 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5005. Min Act: -0.1700
Data Index: 2365117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5005. Min Act: -0.1700
Data Index: 2178571 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.5005. Min Act: -0.1700
Data Index: 6109723 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.4848. Min Act: -0.1700
Data Index: 7792261 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.4848. Min Act: -0.1700
Data Index: 425976 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.4692. Min Act: -0.1700
Data Index: 3136754 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7040. Min Range: -3.7040
Max Act: 3.4848. Min Act: -0.1700
Data Index: 5493778 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19