Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.3200. Min Act: -0.1700
Data Index: 4528925 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.3200. Min Act: -0.1700
Data Index: 3548453 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.1950. Min Act: -0.1700
Data Index: 6719024 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.1638. Min Act: -0.1700
Data Index: 7973387 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.1950. Min Act: -0.1700
Data Index: 2058775 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.1638. Min Act: -0.1700
Data Index: 114374 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.1325. Min Act: -0.1700
Data Index: 8557778 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.1013. Min Act: -0.1700
Data Index: 277727 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.0700. Min Act: -0.1700
Data Index: 1950533 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.0388. Min Act: -0.1700
Data Index: 519918 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.0075. Min Act: -0.1700
Data Index: 1878768 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.0388. Min Act: -0.1700
Data Index: 5132990 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.0075. Min Act: -0.1700
Data Index: 6409791 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3200. Min Range: -6.3200
Max Act: 6.0075. Min Act: -0.1700
Data Index: 2512442 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3200. Min Range: -6.3200
Max Act: 5.9763. Min Act: -0.1700
Data Index: 1398063 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3200. Min Range: -6.3200
Max Act: 5.9763. Min Act: -0.1700
Data Index: 2309236 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3200. Min Range: -6.3200
Max Act: 5.9450. Min Act: -0.1700
Data Index: 5673288 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3200. Min Range: -6.3200
Max Act: 5.9763. Min Act: -0.1700
Data Index: 1382841 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3200. Min Range: -6.3200
Max Act: 5.9450. Min Act: -0.1700
Data Index: 2527540 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3200. Min Range: -6.3200
Max Act: 5.9450. Min Act: -0.1700
Data Index: 3917674 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19