Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.3869. Min Act: -0.1700
Data Index: 3802292 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.3869. Min Act: -0.1700
Data Index: 3338274 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.3869. Min Act: -0.1700
Data Index: 1839787 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.3556. Min Act: -0.1700
Data Index: 551397 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.3244. Min Act: -0.1700
Data Index: 1192020 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.2306. Min Act: -0.1700
Data Index: 4067038 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.2931. Min Act: -0.1700
Data Index: 3431677 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1994. Min Act: -0.1700
Data Index: 1031700 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.2306. Min Act: -0.1700
Data Index: 7513461 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.2306. Min Act: -0.1700
Data Index: 4911036 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1994. Min Act: -0.1700
Data Index: 1914293 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1681. Min Act: -0.1700
Data Index: 5894260 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1369. Min Act: -0.1700
Data Index: 1432779 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1369. Min Act: -0.1700
Data Index: 628982 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1681. Min Act: -0.1700
Data Index: 3131868 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1369. Min Act: -0.1700
Data Index: 1799050 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1056. Min Act: -0.1700
Data Index: 6264408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1056. Min Act: -0.1700
Data Index: 4140225 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1056. Min Act: -0.1700
Data Index: 5161239 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3869. Min Range: -5.3869
Max Act: 5.1056. Min Act: -0.1700
Data Index: 6071675 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19