Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3760 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.1983. Min Act: -0.1700
Data Index: 7633220 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.1358. Min Act: -0.1700
Data Index: 6859790 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.1358. Min Act: -0.1700
Data Index: 1723905 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1983. Min Range: -7.1983
Max Act: 7.0733. Min Act: -0.1700
Data Index: 69726 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.9795. Min Act: -0.1700
Data Index: 190487 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8858. Min Act: -0.1700
Data Index: 5669532 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8858. Min Act: -0.1700
Data Index: 3043543 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 2715938 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 6203512 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.8233. Min Act: -0.1700
Data Index: 6182558 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.7920. Min Act: -0.1700
Data Index: 2552110 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.7608. Min Act: -0.1700
Data Index: 6483881 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.7608. Min Act: -0.1700
Data Index: 7531722 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.7608. Min Act: -0.1700
Data Index: 1861743 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.7295. Min Act: -0.1700
Data Index: 864741 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.6670. Min Act: -0.1700
Data Index: 2613718 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.6983. Min Act: -0.1700
Data Index: 1411119 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.6983. Min Act: -0.1700
Data Index: 3701859 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.6983. Min Act: -0.1700
Data Index: 2993289 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1983. Min Range: -7.1983
Max Act: 6.6983. Min Act: -0.1700
Data Index: 1705855 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19