Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 594 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.9663. Min Act: -0.1700
Data Index: 7258171 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.6692. Min Act: -0.1700
Data Index: 3246127 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.6379. Min Act: -0.1700
Data Index: 1967409 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.6379. Min Act: -0.1700
Data Index: 2267945 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.6379. Min Act: -0.1700
Data Index: 856312 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.6379. Min Act: -0.1700
Data Index: 2759115 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.6223. Min Act: -0.1700
Data Index: 2391773 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.6223. Min Act: -0.1700
Data Index: 2293277 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.5910. Min Act: -0.1700
Data Index: 7581117 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.5753. Min Act: -0.1700
Data Index: 3912583 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.5597. Min Act: -0.1700
Data Index: 1967411 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.5440. Min Act: -0.1700
Data Index: 2267947 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.5597. Min Act: -0.1700
Data Index: 7877402 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.5440. Min Act: -0.1700
Data Index: 5715583 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.5127. Min Act: -0.1700
Data Index: 2986584 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.4970. Min Act: -0.1700
Data Index: 1967408 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.4970. Min Act: -0.1700
Data Index: 7204092 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.4970. Min Act: -0.1700
Data Index: 5715582 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.4814. Min Act: -0.1700
Data Index: 6084201 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9663. Min Range: -3.9663
Max Act: 3.4814. Min Act: -0.1700
Data Index: 7082675 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19