Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.8458. Min Act: -0.1700
Data Index: 1220967 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.8146. Min Act: -0.1700
Data Index: 1173945 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.7208. Min Act: -0.1700
Data Index: 6718061 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.7208. Min Act: -0.1700
Data Index: 8754684 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.7208. Min Act: -0.1700
Data Index: 1101732 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.6896. Min Act: -0.1700
Data Index: 5730885 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.6583. Min Act: -0.1700
Data Index: 1610567 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.6583. Min Act: -0.1700
Data Index: 4935921 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.6583. Min Act: -0.1700
Data Index: 4935395 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5958. Min Act: -0.1700
Data Index: 8005435 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5958. Min Act: -0.1700
Data Index: 1093302 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5646. Min Act: -0.1700
Data Index: 6483829 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5646. Min Act: -0.1700
Data Index: 1890358 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5958. Min Act: -0.1700
Data Index: 4733523 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5646. Min Act: -0.1700
Data Index: 2315971 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5646. Min Act: -0.1700
Data Index: 3545266 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5333. Min Act: -0.1700
Data Index: 4296654 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5021. Min Act: -0.1700
Data Index: 6506325 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.4708. Min Act: -0.1700
Data Index: 6360748 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8458. Min Range: -4.8458
Max Act: 4.5021. Min Act: -0.1700
Data Index: 4983267 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19