Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 962 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2118. Min Range: -4.2118
Max Act: 4.2118. Min Act: -0.1700
Data Index: 3836406 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2118. Min Range: -4.2118
Max Act: 4.0868. Min Act: -0.1700
Data Index: 7235572 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2118. Min Range: -4.2118
Max Act: 4.0556. Min Act: -0.1700
Data Index: 1714099 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2118. Min Range: -4.2118
Max Act: 4.0556. Min Act: -0.1700
Data Index: 8544223 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.9930. Min Act: -0.1700
Data Index: 6732532 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.9618. Min Act: -0.1700
Data Index: 7641824 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8993. Min Act: -0.1700
Data Index: 1846174 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8680. Min Act: -0.1700
Data Index: 6096287 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8367. Min Act: -0.1700
Data Index: 3840930 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8367. Min Act: -0.1700
Data Index: 3260930 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8367. Min Act: -0.1700
Data Index: 2453736 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8054. Min Act: -0.1700
Data Index: 3420551 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8680. Min Act: -0.1700
Data Index: 595437 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8054. Min Act: -0.1700
Data Index: 1947591 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8054. Min Act: -0.1700
Data Index: 3543937 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8054. Min Act: -0.1700
Data Index: 5578267 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.7898. Min Act: -0.1700
Data Index: 4332098 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8054. Min Act: -0.1700
Data Index: 1923173 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.7742. Min Act: -0.1700
Data Index: 3810277 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2118. Min Range: -4.2118
Max Act: 3.8054. Min Act: -0.1700
Data Index: 3896991 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19