Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 637 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0207. Min Range: -4.0207
Max Act: 4.0207. Min Act: -0.1700
Data Index: 1279403 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.9895. Min Act: -0.1700
Data Index: 4956504 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1092425 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.9582. Min Act: -0.1700
Data Index: 2566257 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.9426. Min Act: -0.1700
Data Index: 4934387 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.9426. Min Act: -0.1700
Data Index: 2236344 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.9269. Min Act: -0.1700
Data Index: 3230195 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8957. Min Act: -0.1700
Data Index: 1587138 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8957. Min Act: -0.1700
Data Index: 2642901 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8488. Min Act: -0.1700
Data Index: 3942661 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8644. Min Act: -0.1700
Data Index: 7160978 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8488. Min Act: -0.1700
Data Index: 2464409 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8175. Min Act: -0.1700
Data Index: 6728216 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8175. Min Act: -0.1700
Data Index: 5102090 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8331. Min Act: -0.1700
Data Index: 8756928 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8175. Min Act: -0.1700
Data Index: 4934386 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8175. Min Act: -0.1700
Data Index: 3372925 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8019. Min Act: -0.1700
Data Index: 5041597 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8019. Min Act: -0.1700
Data Index: 7288237 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0207. Min Range: -4.0207
Max Act: 3.8019. Min Act: -0.1700
Data Index: 6639655 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19