Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2747 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0710. Min Range: -4.0710
Max Act: 4.0710. Min Act: -0.1700
Data Index: 2251920 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0710. Min Range: -4.0710
Max Act: 4.0710. Min Act: -0.1700
Data Index: 1589014 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0710. Min Range: -4.0710
Max Act: 4.0710. Min Act: -0.1700
Data Index: 4697127 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.9772. Min Act: -0.1700
Data Index: 3160663 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.9303. Min Act: -0.1700
Data Index: 5029954 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.9147. Min Act: -0.1700
Data Index: 4634370 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8991. Min Act: -0.1700
Data Index: 269055 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8991. Min Act: -0.1700
Data Index: 8591729 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8834. Min Act: -0.1700
Data Index: 4680484 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8991. Min Act: -0.1700
Data Index: 2379400 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8522. Min Act: -0.1700
Data Index: 5507283 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8678. Min Act: -0.1700
Data Index: 1863958 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8522. Min Act: -0.1700
Data Index: 5453864 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8522. Min Act: -0.1700
Data Index: 5212350 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8834. Min Act: -0.1700
Data Index: 5930421 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8365. Min Act: -0.1700
Data Index: 5117424 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8522. Min Act: -0.1700
Data Index: 1637464 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8522. Min Act: -0.1700
Data Index: 606661 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8209. Min Act: -0.1700
Data Index: 2533350 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0710. Min Range: -4.0710
Max Act: 3.8365. Min Act: -0.1700
Data Index: 3352871 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19