Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1556 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.6183. Min Act: -0.1700
Data Index: 7252651 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.5557. Min Act: -0.1700
Data Index: 5440675 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.5557. Min Act: -0.1700
Data Index: 3576688 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.5244. Min Act: -0.1700
Data Index: 3883769 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4930. Min Act: -0.1700
Data Index: 7279251 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4930. Min Act: -0.1700
Data Index: 2468861 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4774. Min Act: -0.1700
Data Index: 5079919 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4774. Min Act: -0.1700
Data Index: 6022206 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4617. Min Act: -0.1700
Data Index: 2373712 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4617. Min Act: -0.1700
Data Index: 4917233 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4460. Min Act: -0.1700
Data Index: 8585874 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4147. Min Act: -0.1700
Data Index: 558493 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.4147. Min Act: -0.1700
Data Index: 2672269 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.3990. Min Act: -0.1700
Data Index: 1059824 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.3990. Min Act: -0.1700
Data Index: 5838411 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.3990. Min Act: -0.1700
Data Index: 603203 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.3833. Min Act: -0.1700
Data Index: 6844319 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.3990. Min Act: -0.1700
Data Index: 277733 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.3833. Min Act: -0.1700
Data Index: 590131 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6183. Min Range: -3.6183
Max Act: 3.3676. Min Act: -0.1700
Data Index: 6510526 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19