Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0922. Min Range: -6.0922
Max Act: 6.0922. Min Act: -0.1700
Data Index: 1203696 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0922. Min Range: -6.0922
Max Act: 6.0922. Min Act: -0.1700
Data Index: 4896957 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.9360. Min Act: -0.1700
Data Index: 5177936 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.8422. Min Act: -0.1700
Data Index: 1080869 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.7797. Min Act: -0.1700
Data Index: 4354823 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.7797. Min Act: -0.1700
Data Index: 5383793 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.7797. Min Act: -0.1700
Data Index: 8774586 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.7797. Min Act: -0.1700
Data Index: 1190048 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.7797. Min Act: -0.1700
Data Index: 6207709 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.7485. Min Act: -0.1700
Data Index: 6645541 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.7172. Min Act: -0.1700
Data Index: 7274853 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6547. Min Act: -0.1700
Data Index: 6866585 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6547. Min Act: -0.1700
Data Index: 1978808 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6860. Min Act: -0.1700
Data Index: 6296948 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6860. Min Act: -0.1700
Data Index: 403118 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6860. Min Act: -0.1700
Data Index: 8088592 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6547. Min Act: -0.1700
Data Index: 3267509 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6235. Min Act: -0.1700
Data Index: 2309553 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6235. Min Act: -0.1700
Data Index: 3675815 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0922. Min Range: -6.0922
Max Act: 5.6235. Min Act: -0.1700
Data Index: 2320396 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19