Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.8244. Min Act: -0.1700
Data Index: 2180389 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.7619. Min Act: -0.1700
Data Index: 8237142 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.7306. Min Act: -0.1700
Data Index: 1820967 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.6994. Min Act: -0.1700
Data Index: 4759804 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.6056. Min Act: -0.1700
Data Index: 1033519 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.6056. Min Act: -0.1700
Data Index: 2077290 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.6056. Min Act: -0.1700
Data Index: 4744883 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.5744. Min Act: -0.1700
Data Index: 6312019 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.5431. Min Act: -0.1700
Data Index: 3483571 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.5431. Min Act: -0.1700
Data Index: 1981019 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.5119. Min Act: -0.1700
Data Index: 7301426 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.4494. Min Act: -0.1700
Data Index: 6076312 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.4181. Min Act: -0.1700
Data Index: 5747909 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.4181. Min Act: -0.1700
Data Index: 7722952 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.4181. Min Act: -0.1700
Data Index: 3317026 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.3869. Min Act: -0.1700
Data Index: 6107146 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.3869. Min Act: -0.1700
Data Index: 4995029 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.3869. Min Act: -0.1700
Data Index: 7419342 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.3869. Min Act: -0.1700
Data Index: 8393471 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8244. Min Range: -6.8244
Max Act: 6.3869. Min Act: -0.1700
Data Index: 1797708 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19