Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2263. Min Range: -6.2263
Max Act: 6.2263. Min Act: -0.1700
Data Index: 7718605 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2263. Min Range: -6.2263
Max Act: 6.1326. Min Act: -0.1700
Data Index: 4796003 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2263. Min Range: -6.2263
Max Act: 6.1326. Min Act: -0.1700
Data Index: 5237271 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2263. Min Range: -6.2263
Max Act: 6.0076. Min Act: -0.1700
Data Index: 213922 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.9763. Min Act: -0.1700
Data Index: 1410123 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8826. Min Act: -0.1700
Data Index: 5086992 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.9138. Min Act: -0.1700
Data Index: 6791558 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.9138. Min Act: -0.1700
Data Index: 1814946 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.9138. Min Act: -0.1700
Data Index: 4139574 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8826. Min Act: -0.1700
Data Index: 3824303 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8826. Min Act: -0.1700
Data Index: 5923967 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8513. Min Act: -0.1700
Data Index: 4418089 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8513. Min Act: -0.1700
Data Index: 4439066 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8201. Min Act: -0.1700
Data Index: 5974220 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8513. Min Act: -0.1700
Data Index: 7885243 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8201. Min Act: -0.1700
Data Index: 8014219 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.8201. Min Act: -0.1700
Data Index: 4903467 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.7888. Min Act: -0.1700
Data Index: 5404096 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.7888. Min Act: -0.1700
Data Index: 6338626 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2263. Min Range: -6.2263
Max Act: 5.7576. Min Act: -0.1700
Data Index: 1933035 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19