Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2711 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.8413. Min Act: -0.1700
Data Index: 3911632 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.7319. Min Act: -0.1700
Data Index: 2346552 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.7319. Min Act: -0.1700
Data Index: 395636 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.6380. Min Act: -0.1700
Data Index: 5267158 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.5284. Min Act: -0.1700
Data Index: 4475604 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.5441. Min Act: -0.1700
Data Index: 1221322 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4971. Min Act: -0.1700
Data Index: 6495400 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4814. Min Act: -0.1700
Data Index: 1206795 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4658. Min Act: -0.1700
Data Index: 6842958 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4814. Min Act: -0.1700
Data Index: 2891126 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4658. Min Act: -0.1700
Data Index: 8452428 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4658. Min Act: -0.1700
Data Index: 4654397 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4658. Min Act: -0.1700
Data Index: 6612966 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4501. Min Act: -0.1700
Data Index: 5676622 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4344. Min Act: -0.1700
Data Index: 6637938 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4501. Min Act: -0.1700
Data Index: 910821 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4501. Min Act: -0.1700
Data Index: 2380607 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4344. Min Act: -0.1700
Data Index: 4266620 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4344. Min Act: -0.1700
Data Index: 1092275 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8413. Min Range: -3.8413
Max Act: 3.4188. Min Act: -0.1700
Data Index: 251572 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19