Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2270 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.7390. Min Act: -0.1700
Data Index: 15904 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.6452. Min Act: -0.1700
Data Index: 25368 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.4265. Min Act: -0.1700
Data Index: 7438731 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.3327. Min Act: -0.1700
Data Index: 2583203 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2702. Min Act: -0.1700
Data Index: 4937298 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2390. Min Act: -0.1700
Data Index: 7244696 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.3015. Min Act: -0.1700
Data Index: 1103388 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2390. Min Act: -0.1700
Data Index: 6125062 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2390. Min Act: -0.1700
Data Index: 7738736 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2702. Min Act: -0.1700
Data Index: 1349027 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2390. Min Act: -0.1700
Data Index: 7176552 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2390. Min Act: -0.1700
Data Index: 6495129 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2077. Min Act: -0.1700
Data Index: 1428325 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2390. Min Act: -0.1700
Data Index: 8509092 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.2077. Min Act: -0.1700
Data Index: 5770820 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.1765. Min Act: -0.1700
Data Index: 5196662 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.1765. Min Act: -0.1700
Data Index: 2536208 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.1452. Min Act: -0.1700
Data Index: 3975740 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.1452. Min Act: -0.1700
Data Index: 6510370 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7390. Min Range: -6.7390
Max Act: 6.1452. Min Act: -0.1700
Data Index: 5390022 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19