Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4562 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0499. Min Range: -7.0499
Max Act: 7.0499. Min Act: -0.1700
Data Index: 7990789 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.9874. Min Act: -0.1700
Data Index: 6759700 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.9249. Min Act: -0.1700
Data Index: 7224896 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.8311. Min Act: -0.1700
Data Index: 2725269 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.8311. Min Act: -0.1700
Data Index: 4472647 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.8311. Min Act: -0.1700
Data Index: 1266877 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.7686. Min Act: -0.1700
Data Index: 5555400 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.7686. Min Act: -0.1700
Data Index: 4416076 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.7374. Min Act: -0.1700
Data Index: 8198134 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.7061. Min Act: -0.1700
Data Index: 8316835 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.7061. Min Act: -0.1700
Data Index: 7567841 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.6749. Min Act: -0.1700
Data Index: 699337 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5186. Min Act: -0.1700
Data Index: 1153394 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5499. Min Act: -0.1700
Data Index: 2918325 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5499. Min Act: -0.1700
Data Index: 5992029 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5499. Min Act: -0.1700
Data Index: 1706350 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5186. Min Act: -0.1700
Data Index: 5890597 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5186. Min Act: -0.1700
Data Index: 3312875 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5186. Min Act: -0.1700
Data Index: 7041791 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0499. Min Range: -7.0499
Max Act: 6.5186. Min Act: -0.1700
Data Index: 8361861 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19