Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5773 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4573. Min Range: -5.4573
Max Act: 5.4573. Min Act: -0.1700
Data Index: 4721278 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4573. Min Range: -5.4573
Max Act: 5.3323. Min Act: -0.1700
Data Index: 564992 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4573. Min Range: -5.4573
Max Act: 5.3323. Min Act: -0.1700
Data Index: 4773226 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4573. Min Range: -5.4573
Max Act: 5.0823. Min Act: -0.1700
Data Index: 6739653 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4573. Min Range: -5.4573
Max Act: 5.1135. Min Act: -0.1700
Data Index: 5359906 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4573. Min Range: -5.4573
Max Act: 5.0823. Min Act: -0.1700
Data Index: 7585512 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9573. Min Act: -0.1700
Data Index: 5631870 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9573. Min Act: -0.1700
Data Index: 358784 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9885. Min Act: -0.1700
Data Index: 6981812 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9573. Min Act: -0.1700
Data Index: 6532451 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9573. Min Act: -0.1700
Data Index: 426226 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9573. Min Act: -0.1700
Data Index: 181680 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9260. Min Act: -0.1700
Data Index: 8144010 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9573. Min Act: -0.1700
Data Index: 8077139 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9260. Min Act: -0.1700
Data Index: 452216 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9260. Min Act: -0.1700
Data Index: 2052512 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9260. Min Act: -0.1700
Data Index: 2288041 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.9260. Min Act: -0.1700
Data Index: 7243382 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.8948. Min Act: -0.1700
Data Index: 5622427 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4573. Min Range: -5.4573
Max Act: 4.8948. Min Act: -0.1700
Data Index: 119028 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19