Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.9369. Min Act: -0.1700
Data Index: 8027651 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.9369. Min Act: -0.1700
Data Index: 7222942 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.8118. Min Act: -0.1700
Data Index: 7931252 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.8118. Min Act: -0.1700
Data Index: 7931253 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.7649. Min Act: -0.1700
Data Index: 8170973 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.7649. Min Act: -0.1700
Data Index: 4511892 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.7493. Min Act: -0.1700
Data Index: 6505337 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.6867. Min Act: -0.1700
Data Index: 5056421 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.6554. Min Act: -0.1700
Data Index: 5950727 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.6398. Min Act: -0.1700
Data Index: 1923042 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.5928. Min Act: -0.1700
Data Index: 2747272 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.6085. Min Act: -0.1700
Data Index: 2523185 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.5928. Min Act: -0.1700
Data Index: 1111856 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.5772. Min Act: -0.1700
Data Index: 7788378 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.6085. Min Act: -0.1700
Data Index: 3124245 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.6241. Min Act: -0.1700
Data Index: 2029790 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.5928. Min Act: -0.1700
Data Index: 7462018 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.5615. Min Act: -0.1700
Data Index: 5678646 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.5772. Min Act: -0.1700
Data Index: 1790206 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9369. Min Range: -3.9369
Max Act: 3.5459. Min Act: -0.1700
Data Index: 5897608 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19