Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 633 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.3548. Min Act: -0.1700
Data Index: 3707038 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.2920. Min Act: -0.1700
Data Index: 852624 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1977. Min Act: -0.1700
Data Index: 7123854 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1977. Min Act: -0.1700
Data Index: 959018 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1977. Min Act: -0.1700
Data Index: 2753161 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1820. Min Act: -0.1700
Data Index: 8019797 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1820. Min Act: -0.1700
Data Index: 1274594 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1505. Min Act: -0.1700
Data Index: 2983446 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1663. Min Act: -0.1700
Data Index: 5561164 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1505. Min Act: -0.1700
Data Index: 135600 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1505. Min Act: -0.1700
Data Index: 3539019 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1505. Min Act: -0.1700
Data Index: 3429212 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1505. Min Act: -0.1700
Data Index: 7808011 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1348. Min Act: -0.1700
Data Index: 6431596 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1348. Min Act: -0.1700
Data Index: 5140130 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1190. Min Act: -0.1700
Data Index: 5690472 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1033. Min Act: -0.1700
Data Index: 6035605 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1190. Min Act: -0.1700
Data Index: 5884015 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1190. Min Act: -0.1700
Data Index: 2126498 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3548. Min Range: -3.3548
Max Act: 3.1033. Min Act: -0.1700
Data Index: 4490880 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19