Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.9233. Min Act: -0.1700
Data Index: 8279579 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.9075. Min Act: -0.1700
Data Index: 4079994 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8757. Min Act: -0.1700
Data Index: 8490519 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8757. Min Act: -0.1700
Data Index: 3308610 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8598. Min Act: -0.1700
Data Index: 5831555 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8598. Min Act: -0.1700
Data Index: 1193881 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8598. Min Act: -0.1700
Data Index: 8112746 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8440. Min Act: -0.1700
Data Index: 4712459 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8281. Min Act: -0.1700
Data Index: 4036382 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8440. Min Act: -0.1700
Data Index: 90055 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8598. Min Act: -0.1700
Data Index: 3545461 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8281. Min Act: -0.1700
Data Index: 1955578 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8281. Min Act: -0.1700
Data Index: 2061583 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8281. Min Act: -0.1700
Data Index: 1119210 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8122. Min Act: -0.1700
Data Index: 5903833 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8122. Min Act: -0.1700
Data Index: 4593949 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8122. Min Act: -0.1700
Data Index: 4770446 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8122. Min Act: -0.1700
Data Index: 1461864 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8122. Min Act: -0.1700
Data Index: 7090556 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9233. Min Range: -2.9233
Max Act: 2.8122. Min Act: -0.1700
Data Index: 3501357 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19