Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5562 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.5259. Min Act: -0.1700
Data Index: 1240013 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.2446. Min Act: -0.1700
Data Index: 1033408 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.1821. Min Act: -0.1700
Data Index: 6329207 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.1196. Min Act: -0.1699
Data Index: 6420092 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.0571. Min Act: -0.1700
Data Index: 777859 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.0571. Min Act: -0.1700
Data Index: 1054178 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.0259. Min Act: -0.1700
Data Index: 6733308 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.0259. Min Act: -0.1700
Data Index: 2047514 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5259. Min Range: -7.5259
Max Act: 7.0259. Min Act: -0.1700
Data Index: 7766328 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9321. Min Act: -0.1700
Data Index: 5951591 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9321. Min Act: -0.1700
Data Index: 334906 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9321. Min Act: -0.1700
Data Index: 373744 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9321. Min Act: -0.1700
Data Index: 8741187 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9321. Min Act: -0.1700
Data Index: 4014434 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9321. Min Act: -0.1700
Data Index: 3895098 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9009. Min Act: -0.1700
Data Index: 112347 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.9009. Min Act: -0.1700
Data Index: 8724576 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.8696. Min Act: -0.1700
Data Index: 5103955 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.8696. Min Act: -0.1700
Data Index: 3912301 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5259. Min Range: -7.5259
Max Act: 6.8696. Min Act: -0.1700
Data Index: 6670910 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19