Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.8658. Min Act: -0.1700
Data Index: 5409472 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.7720. Min Act: -0.1700
Data Index: 6547487 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.7407. Min Act: -0.1700
Data Index: 2190950 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.6938. Min Act: -0.1700
Data Index: 8132302 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.6469. Min Act: -0.1700
Data Index: 6764161 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.6469. Min Act: -0.1700
Data Index: 7802744 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.6469. Min Act: -0.1700
Data Index: 3948282 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.5999. Min Act: -0.1700
Data Index: 92975 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.5686. Min Act: -0.1700
Data Index: 4896483 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.5373. Min Act: -0.1700
Data Index: 2304576 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.5530. Min Act: -0.1700
Data Index: 8426842 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.5217. Min Act: -0.1700
Data Index: 8249113 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.5060. Min Act: -0.1700
Data Index: 8296605 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.4903. Min Act: -0.1700
Data Index: 7175656 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.4903. Min Act: -0.1700
Data Index: 7460838 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.4433. Min Act: -0.1700
Data Index: 4937884 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.4433. Min Act: -0.1700
Data Index: 2190947 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.4590. Min Act: -0.1700
Data Index: 2219682 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.4277. Min Act: -0.1700
Data Index: 8249114 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8658. Min Range: -3.8658
Max Act: 3.4120. Min Act: -0.1700
Data Index: 6336333 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19