Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5399 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1588. Min Range: -5.1588
Max Act: 5.1588. Min Act: -0.1700
Data Index: 3177289 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1588. Min Range: -5.1588
Max Act: 5.1276. Min Act: -0.1700
Data Index: 8401498 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1588. Min Range: -5.1588
Max Act: 5.1276. Min Act: -0.1700
Data Index: 4088499 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1588. Min Range: -5.1588
Max Act: 5.0026. Min Act: -0.1700
Data Index: 5913928 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.9713. Min Act: -0.1700
Data Index: 347161 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.9401. Min Act: -0.1700
Data Index: 632761 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.9401. Min Act: -0.1700
Data Index: 2465853 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.9401. Min Act: -0.1700
Data Index: 6798820 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.9401. Min Act: -0.1700
Data Index: 8430857 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.9088. Min Act: -0.1700
Data Index: 2420483 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.9088. Min Act: -0.1700
Data Index: 5233124 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8463. Min Act: -0.1700
Data Index: 620045 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8776. Min Act: -0.1700
Data Index: 4303439 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8776. Min Act: -0.1700
Data Index: 8289228 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8776. Min Act: -0.1700
Data Index: 5621119 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8776. Min Act: -0.1700
Data Index: 2297058 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8776. Min Act: -0.1700
Data Index: 5164406 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8151. Min Act: -0.1700
Data Index: 57652 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8151. Min Act: -0.1700
Data Index: 5597809 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1588. Min Range: -5.1588
Max Act: 4.8463. Min Act: -0.1700
Data Index: 6542272 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19