Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 192 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.6509. Min Act: -0.1700
Data Index: 722246 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.6509. Min Act: -0.1700
Data Index: 5312078 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.5259. Min Act: -0.1700
Data Index: 722248 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.5259. Min Act: -0.1700
Data Index: 117459 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.4322. Min Act: -0.1700
Data Index: 7634064 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3072. Min Act: -0.1700
Data Index: 4279358 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3072. Min Act: -0.1700
Data Index: 8521352 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2759. Min Act: -0.1700
Data Index: 2839853 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.3072. Min Act: -0.1700
Data Index: 2085113 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2447. Min Act: -0.1700
Data Index: 5202349 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2134. Min Act: -0.1700
Data Index: 8339686 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2447. Min Act: -0.1700
Data Index: 2666347 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2134. Min Act: -0.1700
Data Index: 4143511 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2447. Min Act: -0.1700
Data Index: 5401432 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.1822. Min Act: -0.1700
Data Index: 8619684 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2134. Min Act: -0.1700
Data Index: 4279361 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.2447. Min Act: -0.1700
Data Index: 1416281 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.1822. Min Act: -0.1700
Data Index: 8072741 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.1509. Min Act: -0.1700
Data Index: 1205736 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6509. Min Range: -5.6509
Max Act: 5.1822. Min Act: -0.1700
Data Index: 4432949 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19