Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.9213. Min Act: -0.1700
Data Index: 1458266 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.6713. Min Act: -0.1700
Data Index: 5566511 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.4526. Min Act: -0.1700
Data Index: 440191 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3588. Min Act: -0.1700
Data Index: 7853007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3901. Min Act: -0.1700
Data Index: 8136810 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.3276. Min Act: -0.1700
Data Index: 300164 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.2963. Min Act: -0.1700
Data Index: 6834427 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.2026. Min Act: -0.1700
Data Index: 4154388 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.2026. Min Act: -0.1700
Data Index: 7870248 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.1401. Min Act: -0.1700
Data Index: 2662090 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.0776. Min Act: -0.1700
Data Index: 4961441 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9213. Min Range: -5.9213
Max Act: 5.0463. Min Act: -0.1700
Data Index: 7864730 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.9838. Min Act: -0.1700
Data Index: 957003 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.9526. Min Act: -0.1700
Data Index: 2599221 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.9526. Min Act: -0.1700
Data Index: 4654924 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.8901. Min Act: -0.1700
Data Index: 8457590 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.9213. Min Act: -0.1700
Data Index: 3698592 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.8901. Min Act: -0.1700
Data Index: 5741653 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.9213. Min Act: -0.1700
Data Index: 1785137 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9213. Min Range: -5.9213
Max Act: 4.8901. Min Act: -0.1700
Data Index: 5785407 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19