Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1600 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5736. Min Act: -0.1700
Data Index: 7211160 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5424. Min Act: -0.1700
Data Index: 4286609 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5424. Min Act: -0.1700
Data Index: 8579389 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 5458605 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 5449175 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 204476 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 1465990 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.5111. Min Act: -0.1700
Data Index: 686014 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4799. Min Act: -0.1700
Data Index: 386684 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4799. Min Act: -0.1700
Data Index: 7445060 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 843678 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 1085560 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 5060420 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 7603015 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4486. Min Act: -0.1700
Data Index: 7100758 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4174. Min Act: -0.1700
Data Index: 623791 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4174. Min Act: -0.1700
Data Index: 5582344 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4174. Min Act: -0.1700
Data Index: 4643210 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4174. Min Act: -0.1700
Data Index: 8804251 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5736. Min Range: -5.5736
Max Act: 5.4174. Min Act: -0.1700
Data Index: 2660587 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19