Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3565 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0418. Min Range: -4.0418
Max Act: 4.0418. Min Act: -0.1700
Data Index: 5112204 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0418. Min Range: -4.0418
Max Act: 4.0418. Min Act: -0.1700
Data Index: 7768269 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0418. Min Range: -4.0418
Max Act: 4.0418. Min Act: -0.1700
Data Index: 3364991 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.9480. Min Act: -0.1700
Data Index: 4495540 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.9793. Min Act: -0.1700
Data Index: 2399609 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.9168. Min Act: -0.1700
Data Index: 2175368 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.9168. Min Act: -0.1700
Data Index: 2411575 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8855. Min Act: -0.1700
Data Index: 1068648 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8855. Min Act: -0.1700
Data Index: 8091397 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8855. Min Act: -0.1700
Data Index: 1902329 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8542. Min Act: -0.1700
Data Index: 7924767 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8542. Min Act: -0.1700
Data Index: 5049376 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8230. Min Act: -0.1700
Data Index: 968067 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8073. Min Act: -0.1700
Data Index: 2671931 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8073. Min Act: -0.1700
Data Index: 6227840 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.7917. Min Act: -0.1700
Data Index: 8778150 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8073. Min Act: -0.1700
Data Index: 2433663 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.8230. Min Act: -0.1700
Data Index: 6782884 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.7917. Min Act: -0.1700
Data Index: 5346588 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0418. Min Range: -4.0418
Max Act: 3.7917. Min Act: -0.1700
Data Index: 1254112 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19