Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 168 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.1736. Min Act: -0.1700
Data Index: 4284209 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.0799. Min Act: -0.1700
Data Index: 6951152 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.0799. Min Act: -0.1700
Data Index: 2083965 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.0486. Min Act: -0.1700
Data Index: 2266964 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.0486. Min Act: -0.1700
Data Index: 36562 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.0486. Min Act: -0.1700
Data Index: 7783311 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.0174. Min Act: -0.1700
Data Index: 6950004 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1736. Min Range: -5.1736
Max Act: 5.0174. Min Act: -0.1700
Data Index: 4748489 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.9861. Min Act: -0.1700
Data Index: 4374008 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.9861. Min Act: -0.1700
Data Index: 2803067 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.9861. Min Act: -0.1700
Data Index: 2378987 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.9861. Min Act: -0.1700
Data Index: 7895151 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.9236. Min Act: -0.1700
Data Index: 461049 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.9236. Min Act: -0.1700
Data Index: 5725844 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.8924. Min Act: -0.1700
Data Index: 5725851 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.8924. Min Act: -0.1700
Data Index: 7174404 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.8924. Min Act: -0.1700
Data Index: 1982477 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.8924. Min Act: -0.1700
Data Index: 697049 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.8924. Min Act: -0.1700
Data Index: 3014913 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1736. Min Range: -5.1736
Max Act: 4.8611. Min Act: -0.1700
Data Index: 2163882 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19