Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2489 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.5552. Min Act: -0.1700
Data Index: 7173583 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.5240. Min Act: -0.1700
Data Index: 3677209 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.4615. Min Act: -0.1700
Data Index: 149876 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.3990. Min Act: -0.1700
Data Index: 4232832 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.4302. Min Act: -0.1700
Data Index: 3118267 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.3365. Min Act: -0.1700
Data Index: 2992462 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.3052. Min Act: -0.1700
Data Index: 7202626 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.2740. Min Act: -0.1700
Data Index: 7028783 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.2115. Min Act: -0.1700
Data Index: 2489651 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.2427. Min Act: -0.1700
Data Index: 8506719 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.2115. Min Act: -0.1700
Data Index: 1684914 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.1802. Min Act: -0.1700
Data Index: 6273072 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.1802. Min Act: -0.1700
Data Index: 7568635 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.1490. Min Act: -0.1700
Data Index: 6698276 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.0865. Min Act: -0.1700
Data Index: 471072 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.0865. Min Act: -0.1700
Data Index: 838667 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.0865. Min Act: -0.1700
Data Index: 7973055 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.0552. Min Act: -0.1700
Data Index: 5597790 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.0240. Min Act: -0.1700
Data Index: 3910735 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5552. Min Range: -6.5552
Max Act: 6.0552. Min Act: -0.1700
Data Index: 3479755 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19