Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2266 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.6519. Min Act: -0.1700
Data Index: 3267754 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.5894. Min Act: -0.1700
Data Index: 3294541 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.5269. Min Act: -0.1700
Data Index: 6695586 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.5581. Min Act: -0.1700
Data Index: 6962985 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.4644. Min Act: -0.1700
Data Index: 6695590 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.4644. Min Act: -0.1700
Data Index: 5148478 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.4331. Min Act: -0.1700
Data Index: 3743239 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.3394. Min Act: -0.1700
Data Index: 5307228 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.3081. Min Act: -0.1700
Data Index: 2597043 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.2769. Min Act: -0.1700
Data Index: 800278 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.3081. Min Act: -0.1700
Data Index: 3361846 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.3081. Min Act: -0.1700
Data Index: 623218 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.2456. Min Act: -0.1700
Data Index: 7096150 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.2456. Min Act: -0.1700
Data Index: 672816 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.1831. Min Act: -0.1700
Data Index: 4334297 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.1831. Min Act: -0.1700
Data Index: 2520149 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.1831. Min Act: -0.1700
Data Index: 7083048 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.1831. Min Act: -0.1700
Data Index: 2324967 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.1831. Min Act: -0.1700
Data Index: 1085749 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6519. Min Range: -6.6519
Max Act: 6.1831. Min Act: -0.1700
Data Index: 4895314 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19