Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1086 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2498. Min Range: -7.2498
Max Act: 7.2498. Min Act: -0.1700
Data Index: 8821725 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2498. Min Range: -7.2498
Max Act: 7.0623. Min Act: -0.1700
Data Index: 5850708 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.9060. Min Act: -0.1700
Data Index: 6214161 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.8748. Min Act: -0.1700
Data Index: 3320623 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.6560. Min Act: -0.1700
Data Index: 2057909 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.6873. Min Act: -0.1700
Data Index: 5818488 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.6248. Min Act: -0.1700
Data Index: 5716092 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.5935. Min Act: -0.1700
Data Index: 6947492 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.5935. Min Act: -0.1700
Data Index: 5080483 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4998. Min Act: -0.1700
Data Index: 1853370 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4998. Min Act: -0.1700
Data Index: 1214002 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4685. Min Act: -0.1700
Data Index: 5628287 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4685. Min Act: -0.1700
Data Index: 5567327 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4373. Min Act: -0.1700
Data Index: 2626755 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4060. Min Act: -0.1700
Data Index: 6623418 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4060. Min Act: -0.1700
Data Index: 1204110 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4060. Min Act: -0.1700
Data Index: 6426039 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.4060. Min Act: -0.1700
Data Index: 8818108 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.3748. Min Act: -0.1700
Data Index: 6112511 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2498. Min Range: -7.2498
Max Act: 6.3748. Min Act: -0.1700
Data Index: 875612 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19