Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2166 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.2970. Min Act: -0.1700
Data Index: 3577140 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.2970. Min Act: -0.1700
Data Index: 6799273 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.2033. Min Act: -0.1700
Data Index: 4620190 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.1720. Min Act: -0.1700
Data Index: 20169 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.1095. Min Act: -0.1700
Data Index: 7968595 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.0783. Min Act: -0.1700
Data Index: 4989780 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.0158. Min Act: -0.1700
Data Index: 455381 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2970. Min Range: -5.2970
Max Act: 5.0470. Min Act: -0.1700
Data Index: 731176 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.9845. Min Act: -0.1700
Data Index: 6686346 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.9845. Min Act: -0.1700
Data Index: 6127365 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.9220. Min Act: -0.1700
Data Index: 7834652 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.9533. Min Act: -0.1700
Data Index: 2041929 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.9533. Min Act: -0.1700
Data Index: 1084532 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.9220. Min Act: -0.1700
Data Index: 3317512 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.9220. Min Act: -0.1700
Data Index: 4700826 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.8908. Min Act: -0.1700
Data Index: 5072686 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.8908. Min Act: -0.1700
Data Index: 1923366 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.8908. Min Act: -0.1700
Data Index: 1436668 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.8908. Min Act: -0.1700
Data Index: 2093591 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2970. Min Range: -5.2970
Max Act: 4.8908. Min Act: -0.1700
Data Index: 1341892 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19