Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0918. Min Range: -6.0918
Max Act: 6.0918. Min Act: -0.1700
Data Index: 1981747 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.9355. Min Act: -0.1700
Data Index: 554013 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.7480. Min Act: -0.1700
Data Index: 8442396 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.6855. Min Act: -0.1700
Data Index: 4439920 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.5605. Min Act: -0.1700
Data Index: 1001808 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.5605. Min Act: -0.1700
Data Index: 4169249 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4980. Min Act: -0.1700
Data Index: 7387859 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.5293. Min Act: -0.1700
Data Index: 4684267 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4980. Min Act: -0.1700
Data Index: 8294874 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4668. Min Act: -0.1700
Data Index: 3268485 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4355. Min Act: -0.1700
Data Index: 369768 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4355. Min Act: -0.1700
Data Index: 3599631 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4668. Min Act: -0.1700
Data Index: 5890029 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4043. Min Act: -0.1700
Data Index: 7591869 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4355. Min Act: -0.1700
Data Index: 243738 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4668. Min Act: -0.1700
Data Index: 684886 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.3730. Min Act: -0.1700
Data Index: 7656706 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4043. Min Act: -0.1700
Data Index: 3218274 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.4043. Min Act: -0.1700
Data Index: 4326309 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0918. Min Range: -6.0918
Max Act: 5.3730. Min Act: -0.1700
Data Index: 3596106 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19