Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.5200. Min Act: -0.1700
Data Index: 5054059 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.4575. Min Act: -0.1700
Data Index: 6452040 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.3325. Min Act: -0.1700
Data Index: 847787 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.3637. Min Act: -0.1700
Data Index: 7006365 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.3012. Min Act: -0.1700
Data Index: 7022026 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2700. Min Act: -0.1700
Data Index: 7289604 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2700. Min Act: -0.1700
Data Index: 2690705 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2387. Min Act: -0.1700
Data Index: 469599 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2387. Min Act: -0.1700
Data Index: 7501422 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2075. Min Act: -0.1700
Data Index: 8110454 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2700. Min Act: -0.1700
Data Index: 5148477 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2075. Min Act: -0.1700
Data Index: 2877381 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.2075. Min Act: -0.1700
Data Index: 6147452 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.1762. Min Act: -0.1700
Data Index: 1987383 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.1762. Min Act: -0.1700
Data Index: 2837068 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.1762. Min Act: -0.1700
Data Index: 6576614 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.1450. Min Act: -0.1700
Data Index: 146898 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.1762. Min Act: -0.1700
Data Index: 5700128 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.1450. Min Act: -0.1700
Data Index: 5285371 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5200. Min Range: -5.5200
Max Act: 5.0825. Min Act: -0.1700
Data Index: 565530 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19