Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1979. Min Range: -4.1979
Max Act: 4.1979. Min Act: -0.1700
Data Index: 2982116 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1979. Min Range: -4.1979
Max Act: 4.0729. Min Act: -0.1700
Data Index: 2855768 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1979. Min Range: -4.1979
Max Act: 4.0417. Min Act: -0.1700
Data Index: 2603017 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.9791. Min Act: -0.1700
Data Index: 6646189 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1979. Min Range: -4.1979
Max Act: 4.0104. Min Act: -0.1700
Data Index: 8346278 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.9166. Min Act: -0.1700
Data Index: 5510547 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.9791. Min Act: -0.1700
Data Index: 6290111 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.9166. Min Act: -0.1700
Data Index: 3097812 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8853. Min Act: -0.1700
Data Index: 4331490 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8853. Min Act: -0.1700
Data Index: 8818944 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8853. Min Act: -0.1700
Data Index: 192256 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.9166. Min Act: -0.1700
Data Index: 2544066 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8853. Min Act: -0.1700
Data Index: 708661 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8541. Min Act: -0.1700
Data Index: 437567 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8853. Min Act: -0.1700
Data Index: 209745 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8541. Min Act: -0.1700
Data Index: 2635403 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.8228. Min Act: -0.1700
Data Index: 5186101 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.7915. Min Act: -0.1700
Data Index: 1851649 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.7915. Min Act: -0.1700
Data Index: 1174854 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1979. Min Range: -4.1979
Max Act: 3.7915. Min Act: -0.1700
Data Index: 1430229 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19