Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.8875. Min Act: -0.1700
Data Index: 8747244 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.8190. Min Act: -0.1681
Data Index: 6268901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7759. Min Act: -0.1700
Data Index: 1694335 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7846. Min Act: -0.1699
Data Index: 6145736 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7846. Min Act: -0.1696
Data Index: 6563979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7759. Min Act: -0.1698
Data Index: 2090834 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7501. Min Act: -0.1657
Data Index: 4122307 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7414. Min Act: -0.1684
Data Index: 8266406 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7414. Min Act: -0.1699
Data Index: 3157945 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7414. Min Act: -0.1700
Data Index: 4985091 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7328. Min Act: -0.1700
Data Index: 6027713 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7328. Min Act: -0.1700
Data Index: 270060 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7501. Min Act: -0.1700
Data Index: 4281539 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7328. Min Act: -0.1700
Data Index: 5063388 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7328. Min Act: -0.1700
Data Index: 3306291 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7241. Min Act: -0.1700
Data Index: 2798253 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7068. Min Act: -0.1700
Data Index: 5926555 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7068. Min Act: -0.1694
Data Index: 884596 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7155. Min Act: -0.1699
Data Index: 1324033 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8875. Min Range: -1.8875
Max Act: 1.7155. Min Act: -0.1700
Data Index: 6144672 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19