Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.4240. Min Act: -0.1700
Data Index: 4477662 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.4240. Min Act: -0.1700
Data Index: 4586419 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3928. Min Act: -0.1700
Data Index: 6318937 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 368421 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3615. Min Act: -0.1700
Data Index: 2869518 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 8623092 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 310274 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 6168722 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 1876971 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 1414999 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 8253278 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.3303. Min Act: -0.1700
Data Index: 6456599 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2990. Min Act: -0.1700
Data Index: 5500303 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2990. Min Act: -0.1700
Data Index: 7137641 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2990. Min Act: -0.1700
Data Index: 2682379 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2678. Min Act: -0.1700
Data Index: 4202892 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2678. Min Act: -0.1700
Data Index: 8480390 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2678. Min Act: -0.1700
Data Index: 6388879 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2678. Min Act: -0.1700
Data Index: 3862581 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4240. Min Range: -6.4240
Max Act: 6.2678. Min Act: -0.1700
Data Index: 2465093 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19