Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2232. Min Range: -6.2232
Max Act: 6.2232. Min Act: -0.1700
Data Index: 7097019 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2232. Min Range: -6.2232
Max Act: 6.1294. Min Act: -0.1700
Data Index: 3198634 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2232. Min Range: -6.2232
Max Act: 6.0044. Min Act: -0.1700
Data Index: 7922089 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.9419. Min Act: -0.1700
Data Index: 4757380 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.6607. Min Act: -0.1700
Data Index: 1802857 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.6607. Min Act: -0.1700
Data Index: 4581637 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.6607. Min Act: -0.1700
Data Index: 2423239 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5982. Min Act: -0.1700
Data Index: 6649377 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5982. Min Act: -0.1700
Data Index: 1631744 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5357. Min Act: -0.1700
Data Index: 8165874 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5357. Min Act: -0.1700
Data Index: 8487743 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5357. Min Act: -0.1700
Data Index: 2881977 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5357. Min Act: -0.1700
Data Index: 6021337 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5044. Min Act: -0.1700
Data Index: 8687120 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.4732. Min Act: -0.1700
Data Index: 5285439 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5044. Min Act: -0.1700
Data Index: 4046253 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.4732. Min Act: -0.1700
Data Index: 8420737 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5044. Min Act: -0.1700
Data Index: 1120135 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.5044. Min Act: -0.1700
Data Index: 1166458 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2232. Min Range: -6.2232
Max Act: 5.4732. Min Act: -0.1700
Data Index: 1326398 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19