Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.5899. Min Act: -0.1700
Data Index: 100569 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.5274. Min Act: -0.1700
Data Index: 6338174 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.4962. Min Act: -0.1700
Data Index: 6927101 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.4962. Min Act: -0.1700
Data Index: 8143935 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.4962. Min Act: -0.1700
Data Index: 1297937 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.4649. Min Act: -0.1700
Data Index: 7776234 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3711. Min Act: -0.1700
Data Index: 8528057 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3711. Min Act: -0.1700
Data Index: 2819679 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3711. Min Act: -0.1700
Data Index: 2566415 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3399. Min Act: -0.1700
Data Index: 3217275 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3399. Min Act: -0.1700
Data Index: 7367019 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3399. Min Act: -0.1700
Data Index: 4988434 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3399. Min Act: -0.1700
Data Index: 4385170 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3399. Min Act: -0.1700
Data Index: 8524910 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3399. Min Act: -0.1700
Data Index: 367209 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3399. Min Act: -0.1700
Data Index: 970155 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3086. Min Act: -0.1700
Data Index: 3974539 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3086. Min Act: -0.1700
Data Index: 2249258 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3086. Min Act: -0.1700
Data Index: 761316 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5899. Min Range: -4.5899
Max Act: 4.3086. Min Act: -0.1700
Data Index: 7159703 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19