Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 404 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.1452. Min Act: -0.1700
Data Index: 5777605 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 4461345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 2714115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0827. Min Act: -0.1700
Data Index: 282542 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0515. Min Act: -0.1700
Data Index: 4354167 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 6588399 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 4567287 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0515. Min Act: -0.1700
Data Index: 7133028 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 1388504 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 3225020 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1700
Data Index: 2025113 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9890. Min Act: -0.1700
Data Index: 2540210 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1452. Min Range: -5.1452
Max Act: 5.0202. Min Act: -0.1699
Data Index: 2083333 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9890. Min Act: -0.1700
Data Index: 79658 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9577. Min Act: -0.1700
Data Index: 1082466 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9890. Min Act: -0.1700
Data Index: 4816323 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9890. Min Act: -0.1700
Data Index: 790094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9890. Min Act: -0.1700
Data Index: 357254 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9890. Min Act: -0.1700
Data Index: 1997086 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1452. Min Range: -5.1452
Max Act: 4.9890. Min Act: -0.1700
Data Index: 5846727 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19