Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.5124. Min Act: -0.1700
Data Index: 3790967 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.4499. Min Act: -0.1700
Data Index: 3790973 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.2936. Min Act: -0.1700
Data Index: 6070553 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.2624. Min Act: -0.1700
Data Index: 3790977 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.2624. Min Act: -0.1700
Data Index: 7512147 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1999. Min Act: -0.1700
Data Index: 268440 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1686. Min Act: -0.1700
Data Index: 8238028 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1999. Min Act: -0.1700
Data Index: 3790962 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1686. Min Act: -0.1700
Data Index: 1642698 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 4315417 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 293324 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 4604903 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.1061. Min Act: -0.1700
Data Index: 494357 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.0749. Min Act: -0.1700
Data Index: 3790958 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.0749. Min Act: -0.1700
Data Index: 2930147 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.0436. Min Act: -0.1700
Data Index: 5776116 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.0124. Min Act: -0.1700
Data Index: 6044556 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.0124. Min Act: -0.1700
Data Index: 2140987 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5124. Min Range: -6.5124
Max Act: 5.9811. Min Act: -0.1700
Data Index: 6044555 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5124. Min Range: -6.5124
Max Act: 6.0124. Min Act: -0.1700
Data Index: 5028628 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19