Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.5306. Min Act: -0.1700
Data Index: 8267406 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.4056. Min Act: -0.1700
Data Index: 2563283 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.3431. Min Act: -0.1700
Data Index: 8450474 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.3431. Min Act: -0.1700
Data Index: 4570921 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.3744. Min Act: -0.1700
Data Index: 2902021 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.3119. Min Act: -0.1700
Data Index: 8225496 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.3119. Min Act: -0.1700
Data Index: 5118887 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2806. Min Act: -0.1700
Data Index: 3644977 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2806. Min Act: -0.1700
Data Index: 523017 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2494. Min Act: -0.1700
Data Index: 1365545 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2494. Min Act: -0.1700
Data Index: 7559442 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2494. Min Act: -0.1700
Data Index: 4569234 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2494. Min Act: -0.1700
Data Index: 1342089 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2181. Min Act: -0.1700
Data Index: 5162980 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.2181. Min Act: -0.1700
Data Index: 3853960 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.1556. Min Act: -0.1700
Data Index: 7499622 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.1556. Min Act: -0.1700
Data Index: 1737348 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.0931. Min Act: -0.1700
Data Index: 7951265 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.1244. Min Act: -0.1700
Data Index: 8606869 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5306. Min Range: -6.5306
Max Act: 6.0619. Min Act: -0.1700
Data Index: 261473 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19