Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2777 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.2565. Min Act: -0.1700
Data Index: 7376732 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.1779. Min Act: -0.1700
Data Index: 8815716 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.1149. Min Act: -0.1700
Data Index: 2014149 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.1307. Min Act: -0.1700
Data Index: 8815710 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0834. Min Act: -0.1700
Data Index: 3687875 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0834. Min Act: -0.1700
Data Index: 1149718 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0834. Min Act: -0.1700
Data Index: 3187273 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0361. Min Act: -0.1700
Data Index: 2516649 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0361. Min Act: -0.1700
Data Index: 7127667 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0518. Min Act: -0.1700
Data Index: 4401681 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0518. Min Act: -0.1700
Data Index: 7731783 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0361. Min Act: -0.1700
Data Index: 947386 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0045. Min Act: -0.1700
Data Index: 1601095 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0203. Min Act: -0.1700
Data Index: 5325233 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0361. Min Act: -0.1700
Data Index: 4666738 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0045. Min Act: -0.1700
Data Index: 4065141 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0361. Min Act: -0.1700
Data Index: 7451498 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0045. Min Act: -0.1700
Data Index: 5570335 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0045. Min Act: -0.1700
Data Index: 6074703 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2565. Min Range: -3.2565
Max Act: 3.0045. Min Act: -0.1700
Data Index: 1067330 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19