Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.4648. Min Act: -0.1700
Data Index: 1206778 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.4336. Min Act: -0.1700
Data Index: 943141 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.3711. Min Act: -0.1700
Data Index: 5939231 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.3398. Min Act: -0.1700
Data Index: 6741837 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.4023. Min Act: -0.1700
Data Index: 6628950 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.3086. Min Act: -0.1700
Data Index: 3076906 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.2773. Min Act: -0.1700
Data Index: 4961239 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.2148. Min Act: -0.1700
Data Index: 5533488 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.2148. Min Act: -0.1700
Data Index: 3651916 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.2148. Min Act: -0.1700
Data Index: 1179979 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.2148. Min Act: -0.1700
Data Index: 1133798 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1523. Min Act: -0.1700
Data Index: 347579 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1835. Min Act: -0.1700
Data Index: 4438257 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1523. Min Act: -0.1700
Data Index: 1970602 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1523. Min Act: -0.1700
Data Index: 7154531 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1523. Min Act: -0.1700
Data Index: 6372323 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1523. Min Act: -0.1700
Data Index: 781084 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1835. Min Act: -0.1700
Data Index: 3227315 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1523. Min Act: -0.1700
Data Index: 3775067 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4648. Min Range: -4.4648
Max Act: 4.1210. Min Act: -0.1700
Data Index: 4454970 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19