Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4716 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0054. Min Range: -4.0054
Max Act: 4.0054. Min Act: -0.1700
Data Index: 4809578 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9428. Min Act: -0.1700
Data Index: 2787269 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9116. Min Act: -0.1700
Data Index: 166730 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9428. Min Act: -0.1700
Data Index: 7923016 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9116. Min Act: -0.1700
Data Index: 1677219 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9116. Min Act: -0.1700
Data Index: 8128868 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9116. Min Act: -0.1700
Data Index: 6615905 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9428. Min Act: -0.1700
Data Index: 5917345 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.9116. Min Act: -0.1700
Data Index: 5868335 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.8803. Min Act: -0.1700
Data Index: 4722858 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.8490. Min Act: -0.1700
Data Index: 3042364 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.8490. Min Act: -0.1700
Data Index: 3109483 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.8490. Min Act: -0.1700
Data Index: 3473827 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.8490. Min Act: -0.1700
Data Index: 209311 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.8021. Min Act: -0.1700
Data Index: 2462937 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.8021. Min Act: -0.1700
Data Index: 5205486 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.7865. Min Act: -0.1700
Data Index: 2260261 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.7865. Min Act: -0.1700
Data Index: 2425093 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.7552. Min Act: -0.1700
Data Index: 3348630 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0054. Min Range: -4.0054
Max Act: 3.7552. Min Act: -0.1700
Data Index: 466393 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19