Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2641. Min Range: -4.2641
Max Act: 4.2641. Min Act: -0.1700
Data Index: 5776441 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2641. Min Range: -4.2641
Max Act: 4.1703. Min Act: -0.1700
Data Index: 5856647 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.9203. Min Act: -0.1700
Data Index: 1300547 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.8890. Min Act: -0.1700
Data Index: 4987730 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.8108. Min Act: -0.1700
Data Index: 7755551 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.8108. Min Act: -0.1700
Data Index: 8700059 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.7483. Min Act: -0.1700
Data Index: 6649241 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.7795. Min Act: -0.1700
Data Index: 1982288 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6857. Min Act: -0.1700
Data Index: 6251893 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.7013. Min Act: -0.1700
Data Index: 8130359 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6857. Min Act: -0.1700
Data Index: 4350799 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6857. Min Act: -0.1700
Data Index: 280224 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6701. Min Act: -0.1700
Data Index: 2839305 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6701. Min Act: -0.1700
Data Index: 555130 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6544. Min Act: -0.1700
Data Index: 684430 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6544. Min Act: -0.1700
Data Index: 2134155 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6544. Min Act: -0.1700
Data Index: 4672018 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6544. Min Act: -0.1700
Data Index: 2160967 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6075. Min Act: -0.1700
Data Index: 4248792 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2641. Min Range: -4.2641
Max Act: 3.6231. Min Act: -0.1700
Data Index: 4394924 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19