Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3913 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0450. Min Range: -5.0450
Max Act: 5.0450. Min Act: -0.1700
Data Index: 7489357 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0450. Min Range: -5.0450
Max Act: 5.0137. Min Act: -0.1700
Data Index: 4266494 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.8575. Min Act: -0.1700
Data Index: 71149 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7950. Min Act: -0.1700
Data Index: 7361671 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.8262. Min Act: -0.1700
Data Index: 4266493 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7637. Min Act: -0.1700
Data Index: 5758472 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7325. Min Act: -0.1700
Data Index: 4660226 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7012. Min Act: -0.1700
Data Index: 5765059 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7012. Min Act: -0.1700
Data Index: 6384136 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6700. Min Act: -0.1700
Data Index: 5175257 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6700. Min Act: -0.1700
Data Index: 4790892 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6700. Min Act: -0.1700
Data Index: 3074187 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 3400684 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 8214329 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 30531 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 8660146 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 5276763 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6075. Min Act: -0.1700
Data Index: 6178041 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6075. Min Act: -0.1700
Data Index: 339787 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6075. Min Act: -0.1700
Data Index: 5661721 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19