Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.6621. Min Act: -0.1700
Data Index: 384714 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.5371. Min Act: -0.1700
Data Index: 384715 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.3809. Min Act: -0.1700
Data Index: 3827543 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.2559. Min Act: -0.1700
Data Index: 1653993 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.2246. Min Act: -0.1700
Data Index: 7933916 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.1309. Min Act: -0.1700
Data Index: 1245142 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0996. Min Act: -0.1700
Data Index: 3818039 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0371. Min Act: -0.1700
Data Index: 210007 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0371. Min Act: -0.1700
Data Index: 7382990 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0371. Min Act: -0.1700
Data Index: 2644906 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0371. Min Act: -0.1700
Data Index: 1653984 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0059. Min Act: -0.1700
Data Index: 3617948 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0059. Min Act: -0.1700
Data Index: 6587546 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6621. Min Range: -5.6621
Max Act: 5.0059. Min Act: -0.1700
Data Index: 1021419 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6621. Min Range: -5.6621
Max Act: 4.9746. Min Act: -0.1700
Data Index: 3574770 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6621. Min Range: -5.6621
Max Act: 4.9434. Min Act: -0.1700
Data Index: 1653980 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6621. Min Range: -5.6621
Max Act: 4.9121. Min Act: -0.1700
Data Index: 2137423 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6621. Min Range: -5.6621
Max Act: 4.8809. Min Act: -0.1700
Data Index: 4876329 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6621. Min Range: -5.6621
Max Act: 4.9434. Min Act: -0.1700
Data Index: 4515912 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6621. Min Range: -5.6621
Max Act: 4.9434. Min Act: -0.1700
Data Index: 1654000 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19