Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.6965. Min Act: -0.1700
Data Index: 7621225 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.6965. Min Act: -0.1700
Data Index: 5006443 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.6026. Min Act: -0.1700
Data Index: 4246086 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.6182. Min Act: -0.1700
Data Index: 6155011 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.6182. Min Act: -0.1700
Data Index: 3451489 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.6182. Min Act: -0.1700
Data Index: 4758463 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.6026. Min Act: -0.1700
Data Index: 6279454 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5713. Min Act: -0.1700
Data Index: 3355524 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5556. Min Act: -0.1700
Data Index: 6514435 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5400. Min Act: -0.1700
Data Index: 2518951 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5243. Min Act: -0.1700
Data Index: 8361974 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5243. Min Act: -0.1700
Data Index: 8704234 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5087. Min Act: -0.1700
Data Index: 160328 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5243. Min Act: -0.1700
Data Index: 2444394 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5087. Min Act: -0.1700
Data Index: 1806114 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.5087. Min Act: -0.1700
Data Index: 335347 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.4930. Min Act: -0.1700
Data Index: 3754819 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.4773. Min Act: -0.1700
Data Index: 7694035 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.4617. Min Act: -0.1700
Data Index: 6044539 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6965. Min Range: -3.6965
Max Act: 3.4773. Min Act: -0.1700
Data Index: 3963119 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19