Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1445 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1716. Min Range: -4.1716
Max Act: 4.1716. Min Act: -0.1700
Data Index: 5287798 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.9840. Min Act: -0.1700
Data Index: 8485642 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.9215. Min Act: -0.1700
Data Index: 6473935 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.9215. Min Act: -0.1700
Data Index: 6657334 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.9215. Min Act: -0.1700
Data Index: 3144914 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.9528. Min Act: -0.1700
Data Index: 737441 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.9215. Min Act: -0.1700
Data Index: 4384528 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8590. Min Act: -0.1700
Data Index: 8427257 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8277. Min Act: -0.1700
Data Index: 2491200 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8590. Min Act: -0.1700
Data Index: 2860249 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8590. Min Act: -0.1700
Data Index: 8493662 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.7964. Min Act: -0.1700
Data Index: 2719489 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8590. Min Act: -0.1700
Data Index: 1903343 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8277. Min Act: -0.1700
Data Index: 1513476 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8277. Min Act: -0.1700
Data Index: 7131186 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.7964. Min Act: -0.1700
Data Index: 6884803 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8590. Min Act: -0.1700
Data Index: 6694917 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8277. Min Act: -0.1700
Data Index: 3671693 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8590. Min Act: -0.1700
Data Index: 2135778 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1716. Min Range: -4.1716
Max Act: 3.8590. Min Act: -0.1700
Data Index: 5859122 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19