Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1400 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.6008. Min Act: -0.1700
Data Index: 5669650 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5538. Min Act: -0.1700
Data Index: 8200916 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5695. Min Act: -0.1700
Data Index: 4178666 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5695. Min Act: -0.1700
Data Index: 4787561 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5382. Min Act: -0.1700
Data Index: 882367 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5225. Min Act: -0.1700
Data Index: 5393778 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5225. Min Act: -0.1700
Data Index: 878675 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5225. Min Act: -0.1700
Data Index: 7174490 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5068. Min Act: -0.1700
Data Index: 8089346 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5068. Min Act: -0.1700
Data Index: 5938274 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4912. Min Act: -0.1700
Data Index: 6720466 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4912. Min Act: -0.1700
Data Index: 5312244 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4912. Min Act: -0.1700
Data Index: 397543 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.5068. Min Act: -0.1700
Data Index: 3552601 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4598. Min Act: -0.1700
Data Index: 7909024 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4755. Min Act: -0.1700
Data Index: 4224278 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4755. Min Act: -0.1700
Data Index: 5579415 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4755. Min Act: -0.1700
Data Index: 551066 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4598. Min Act: -0.1700
Data Index: 7224350 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6008. Min Range: -3.6008
Max Act: 3.4598. Min Act: -0.1700
Data Index: 4604505 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19