Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.5222. Min Act: -0.1700
Data Index: 6953518 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.3972. Min Act: -0.1700
Data Index: 1100786 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2722. Min Act: -0.1700
Data Index: 4234173 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.2410. Min Act: -0.1700
Data Index: 6027473 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.1472. Min Act: -0.1700
Data Index: 139340 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.1160. Min Act: -0.1700
Data Index: 5468028 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5222. Min Range: -7.5222
Max Act: 7.0222. Min Act: -0.1700
Data Index: 4165795 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.9597. Min Act: -0.1700
Data Index: 8755284 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.8972. Min Act: -0.1700
Data Index: 5051770 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.8660. Min Act: -0.1700
Data Index: 2628907 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.8660. Min Act: -0.1700
Data Index: 6266167 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.8660. Min Act: -0.1700
Data Index: 201952 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.8035. Min Act: -0.1700
Data Index: 4984347 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.7722. Min Act: -0.1700
Data Index: 1345993 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.7722. Min Act: -0.1700
Data Index: 7488042 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.7722. Min Act: -0.1700
Data Index: 7579561 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.7722. Min Act: -0.1700
Data Index: 7649796 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.7722. Min Act: -0.1700
Data Index: 5878375 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.8035. Min Act: -0.1700
Data Index: 5594654 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5222. Min Range: -7.5222
Max Act: 6.7410. Min Act: -0.1700
Data Index: 7165913 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19