Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1874 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.3896. Min Act: -0.1699
Data Index: 3738064 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.3896. Min Act: -0.1700
Data Index: 5667332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.3896. Min Act: -0.1700
Data Index: 5408920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.3896. Min Act: -0.1700
Data Index: 1378603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.3270. Min Act: -0.1700
Data Index: 7638035 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.2645. Min Act: -0.1700
Data Index: 4488617 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.2645. Min Act: -0.1700
Data Index: 3855232 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.2333. Min Act: -0.1700
Data Index: 7130732 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.2333. Min Act: -0.1700
Data Index: 5080171 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.2333. Min Act: -0.1700
Data Index: 8429168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.2333. Min Act: -0.1700
Data Index: 6791277 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.2020. Min Act: -0.1700
Data Index: 4803828 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1708. Min Act: -0.1700
Data Index: 3432141 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1708. Min Act: -0.1700
Data Index: 2673133 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1708. Min Act: -0.1700
Data Index: 6197788 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1708. Min Act: -0.1700
Data Index: 1362297 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1395. Min Act: -0.1700
Data Index: 5487809 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1395. Min Act: -0.1700
Data Index: 3271499 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1395. Min Act: -0.1700
Data Index: 5746129 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3896. Min Range: -4.3896
Max Act: 4.1395. Min Act: -0.1700
Data Index: 5902751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19