Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2386 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.8597. Min Act: -0.1700
Data Index: 2882627 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.7035. Min Act: -0.1700
Data Index: 5315838 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.6410. Min Act: -0.1700
Data Index: 4536563 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.6410. Min Act: -0.1700
Data Index: 8103021 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.5785. Min Act: -0.1700
Data Index: 3919707 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.5472. Min Act: -0.1700
Data Index: 2966626 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.5160. Min Act: -0.1700
Data Index: 622322 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.5160. Min Act: -0.1700
Data Index: 3720777 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4535. Min Act: -0.1700
Data Index: 7032509 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4535. Min Act: -0.1700
Data Index: 8356796 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4535. Min Act: -0.1700
Data Index: 8266841 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4535. Min Act: -0.1700
Data Index: 3412260 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4222. Min Act: -0.1700
Data Index: 3746749 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4222. Min Act: -0.1700
Data Index: 3958419 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4222. Min Act: -0.1700
Data Index: 6678574 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4222. Min Act: -0.1700
Data Index: 4926124 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.3910. Min Act: -0.1700
Data Index: 7911849 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.4222. Min Act: -0.1700
Data Index: 5502582 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.3910. Min Act: -0.1700
Data Index: 4003416 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8597. Min Range: -5.8597
Max Act: 5.3910. Min Act: -0.1700
Data Index: 4191896 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19