Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.2658. Min Act: -0.1700
Data Index: 1804176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.2305. Min Act: -0.1700
Data Index: 1998632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.2217. Min Act: -0.1700
Data Index: 4455628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.2129. Min Act: -0.1700
Data Index: 2422827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.2129. Min Act: -0.1700
Data Index: 3429316 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1865. Min Act: -0.1700
Data Index: 4534577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1777. Min Act: -0.1700
Data Index: 1016212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1513. Min Act: -0.1700
Data Index: 5809217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1426. Min Act: -0.1700
Data Index: 5054450 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1513. Min Act: -0.1700
Data Index: 499743 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1513. Min Act: -0.1700
Data Index: 243320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1426. Min Act: -0.1700
Data Index: 1439622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1513. Min Act: -0.1700
Data Index: 677538 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1513. Min Act: -0.1700
Data Index: 2733042 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1426. Min Act: -0.1700
Data Index: 8608199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1426. Min Act: -0.1700
Data Index: 5055648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1338. Min Act: -0.1700
Data Index: 6858000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1338. Min Act: -0.1700
Data Index: 6920534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1250. Min Act: -0.1700
Data Index: 3821519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2658. Min Range: -1.2658
Max Act: 1.1162. Min Act: -0.1700
Data Index: 1618302 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19