Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4976 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.5753. Min Act: -0.1700
Data Index: 4686775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.5128. Min Act: -0.1700
Data Index: 8044169 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.5128. Min Act: -0.1700
Data Index: 5221606 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.4191. Min Act: -0.1700
Data Index: 2844570 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3878. Min Act: -0.1700
Data Index: 7304365 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3878. Min Act: -0.1700
Data Index: 3752634 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3566. Min Act: -0.1700
Data Index: 4071868 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3566. Min Act: -0.1700
Data Index: 160236 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3566. Min Act: -0.1700
Data Index: 1210838 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3566. Min Act: -0.1700
Data Index: 1187726 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3566. Min Act: -0.1700
Data Index: 2080741 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3566. Min Act: -0.1700
Data Index: 7600049 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3566. Min Act: -0.1700
Data Index: 4217585 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3253. Min Act: -0.1700
Data Index: 8536624 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3253. Min Act: -0.1700
Data Index: 6481734 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3253. Min Act: -0.1700
Data Index: 8779018 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3253. Min Act: -0.1700
Data Index: 1466392 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3253. Min Act: -0.1700
Data Index: 7574928 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.3253. Min Act: -0.1700
Data Index: 3800150 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5753. Min Range: -5.5753
Max Act: 5.2941. Min Act: -0.1700
Data Index: 1210840 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19