Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1437 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.8483. Min Act: -0.1700
Data Index: 2857959 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.7858. Min Act: -0.1700
Data Index: 1166164 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.7546. Min Act: -0.1700
Data Index: 2869319 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.6608. Min Act: -0.1700
Data Index: 2869325 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.6608. Min Act: -0.1700
Data Index: 4454 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.6608. Min Act: -0.1700
Data Index: 6368897 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.6296. Min Act: -0.1700
Data Index: 973186 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5983. Min Act: -0.1700
Data Index: 5534629 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5983. Min Act: -0.1700
Data Index: 6305258 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5983. Min Act: -0.1700
Data Index: 2871941 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5671. Min Act: -0.1700
Data Index: 6368895 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5671. Min Act: -0.1700
Data Index: 369045 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5358. Min Act: -0.1700
Data Index: 6305259 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5046. Min Act: -0.1700
Data Index: 5858025 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5046. Min Act: -0.1700
Data Index: 4008068 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.5046. Min Act: -0.1700
Data Index: 2968000 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.4733. Min Act: -0.1700
Data Index: 1586869 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.4733. Min Act: -0.1700
Data Index: 7259676 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.4421. Min Act: -0.1700
Data Index: 4635083 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8483. Min Range: -6.8483
Max Act: 6.4421. Min Act: -0.1700
Data Index: 2292633 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19