Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2358 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.6086. Min Act: -0.1700
Data Index: 6110236 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.4836. Min Act: -0.1700
Data Index: 8370756 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.4211. Min Act: -0.1700
Data Index: 5795322 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.3899. Min Act: -0.1700
Data Index: 7545060 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.3899. Min Act: -0.1700
Data Index: 3490647 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.3586. Min Act: -0.1700
Data Index: 1252846 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.3274. Min Act: -0.1700
Data Index: 4740412 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2649. Min Act: -0.1700
Data Index: 2701224 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2961. Min Act: -0.1700
Data Index: 8144337 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2649. Min Act: -0.1700
Data Index: 6189381 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5916856 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2336. Min Act: -0.1700
Data Index: 5755392 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2336. Min Act: -0.1700
Data Index: 8651972 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.1711. Min Act: -0.1700
Data Index: 2021546 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2024. Min Act: -0.1700
Data Index: 5626144 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.1711. Min Act: -0.1700
Data Index: 3177841 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.1711. Min Act: -0.1700
Data Index: 7944797 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.1711. Min Act: -0.1700
Data Index: 2733719 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.1711. Min Act: -0.1700
Data Index: 4749322 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6086. Min Range: -5.6086
Max Act: 5.2024. Min Act: -0.1700
Data Index: 2505748 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19