Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3791 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.4015. Min Act: -0.1700
Data Index: 4775851 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.1828. Min Act: -0.1700
Data Index: 5908196 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.1515. Min Act: -0.1700
Data Index: 1228570 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.0578. Min Act: -0.1700
Data Index: 8159249 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.0890. Min Act: -0.1700
Data Index: 5908197 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.0890. Min Act: -0.1700
Data Index: 6435205 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.0890. Min Act: -0.1700
Data Index: 6435206 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9952. Min Act: -0.1700
Data Index: 7608161 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4015. Min Range: -4.4015
Max Act: 4.0265. Min Act: -0.1700
Data Index: 2481264 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9952. Min Act: -0.1700
Data Index: 6756637 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9952. Min Act: -0.1700
Data Index: 7477914 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9327. Min Act: -0.1700
Data Index: 4542533 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9327. Min Act: -0.1700
Data Index: 7876463 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9327. Min Act: -0.1700
Data Index: 2114362 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9014. Min Act: -0.1700
Data Index: 168181 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9327. Min Act: -0.1700
Data Index: 7287126 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9014. Min Act: -0.1700
Data Index: 93295 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9014. Min Act: -0.1700
Data Index: 3461054 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9014. Min Act: -0.1700
Data Index: 6276353 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4015. Min Range: -4.4015
Max Act: 3.9327. Min Act: -0.1700
Data Index: 4353985 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19