Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3014. Min Range: -4.3014
Max Act: 4.3014. Min Act: -0.1700
Data Index: 4518739 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3014. Min Range: -4.3014
Max Act: 4.2702. Min Act: -0.1700
Data Index: 4171127 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3014. Min Range: -4.3014
Max Act: 4.2702. Min Act: -0.1700
Data Index: 2367319 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3014. Min Range: -4.3014
Max Act: 4.1139. Min Act: -0.1700
Data Index: 797702 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3014. Min Range: -4.3014
Max Act: 4.0514. Min Act: -0.1700
Data Index: 4726026 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.9889. Min Act: -0.1700
Data Index: 2276705 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.9889. Min Act: -0.1700
Data Index: 3221348 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.9264. Min Act: -0.1700
Data Index: 1903125 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.9264. Min Act: -0.1700
Data Index: 3995910 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.8638. Min Act: -0.1700
Data Index: 688328 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.8638. Min Act: -0.1700
Data Index: 7712219 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.8638. Min Act: -0.1700
Data Index: 1944448 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.8326. Min Act: -0.1700
Data Index: 5248629 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.8326. Min Act: -0.1700
Data Index: 6711883 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.8169. Min Act: -0.1700
Data Index: 1822260 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.7856. Min Act: -0.1700
Data Index: 3619669 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.7856. Min Act: -0.1700
Data Index: 7341968 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.7700. Min Act: -0.1700
Data Index: 1336549 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.7700. Min Act: -0.1700
Data Index: 163847 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3014. Min Range: -4.3014
Max Act: 3.7856. Min Act: -0.1700
Data Index: 5294627 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19