Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4092 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.8132. Min Act: -0.1700
Data Index: 4404814 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.7819. Min Act: -0.1700
Data Index: 6920313 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.6569. Min Act: -0.1700
Data Index: 6960607 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.5944. Min Act: -0.1700
Data Index: 6675302 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.5631. Min Act: -0.1700
Data Index: 3083953 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.4381. Min Act: -0.1700
Data Index: 3600962 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.4381. Min Act: -0.1700
Data Index: 7049385 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.4694. Min Act: -0.1700
Data Index: 3283931 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.4694. Min Act: -0.1700
Data Index: 1570037 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.4694. Min Act: -0.1700
Data Index: 4668446 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.4069. Min Act: -0.1700
Data Index: 7743936 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.4694. Min Act: -0.1700
Data Index: 7111487 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3756. Min Act: -0.1700
Data Index: 4500866 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3756. Min Act: -0.1700
Data Index: 3325307 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3756. Min Act: -0.1700
Data Index: 205173 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3756. Min Act: -0.1700
Data Index: 6855051 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3444. Min Act: -0.1700
Data Index: 6533943 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3444. Min Act: -0.1700
Data Index: 1397343 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3444. Min Act: -0.1700
Data Index: 558500 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8132. Min Range: -4.8132
Max Act: 4.3444. Min Act: -0.1700
Data Index: 5172199 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19