Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 850 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.8285. Min Act: -0.1700
Data Index: 2819755 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.7348. Min Act: -0.1700
Data Index: 928058 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.5785. Min Act: -0.1700
Data Index: 4526093 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.5785. Min Act: -0.1700
Data Index: 19052 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.4848. Min Act: -0.1700
Data Index: 4115186 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.4848. Min Act: -0.1700
Data Index: 8487110 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.4223. Min Act: -0.1700
Data Index: 3230529 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.4223. Min Act: -0.1700
Data Index: 2334310 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.4223. Min Act: -0.1700
Data Index: 6818018 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.4223. Min Act: -0.1700
Data Index: 7289359 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.4223. Min Act: -0.1700
Data Index: 1512974 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3910. Min Act: -0.1700
Data Index: 3191107 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3910. Min Act: -0.1700
Data Index: 3149048 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3910. Min Act: -0.1700
Data Index: 8020538 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3910. Min Act: -0.1700
Data Index: 2480875 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3910. Min Act: -0.1700
Data Index: 5909634 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3598. Min Act: -0.1700
Data Index: 5546697 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3598. Min Act: -0.1700
Data Index: 8216332 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3598. Min Act: -0.1700
Data Index: 6982324 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8285. Min Range: -5.8285
Max Act: 5.3285. Min Act: -0.1700
Data Index: 3382908 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19