Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.3017. Min Act: -0.1700
Data Index: 5181595 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.2703. Min Act: -0.1700
Data Index: 5562060 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.2546. Min Act: -0.1700
Data Index: 5093864 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.2546. Min Act: -0.1700
Data Index: 1486600 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.2546. Min Act: -0.1700
Data Index: 5481495 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.2232. Min Act: -0.1700
Data Index: 5227262 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.1760. Min Act: -0.1700
Data Index: 5181391 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.1445. Min Act: -0.1700
Data Index: 2230011 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.1445. Min Act: -0.1700
Data Index: 2097106 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.1288. Min Act: -0.1700
Data Index: 4386402 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.1288. Min Act: -0.1700
Data Index: 5961189 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0973. Min Act: -0.1700
Data Index: 1929335 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0973. Min Act: -0.1700
Data Index: 4526272 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0657. Min Act: -0.1700
Data Index: 1509529 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0657. Min Act: -0.1700
Data Index: 660974 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0815. Min Act: -0.1700
Data Index: 4026805 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0657. Min Act: -0.1700
Data Index: 4224298 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0342. Min Act: -0.1700
Data Index: 6249010 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0500. Min Act: -0.1700
Data Index: 2391481 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3017. Min Range: -3.3017
Max Act: 3.0500. Min Act: -0.1700
Data Index: 3871969 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19