Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.4328. Min Act: -0.1700
Data Index: 5667290 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.4015. Min Act: -0.1700
Data Index: 4609154 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.3703. Min Act: -0.1700
Data Index: 825667 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.3078. Min Act: -0.1700
Data Index: 674178 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.2453. Min Act: -0.1700
Data Index: 4571163 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.2140. Min Act: -0.1700
Data Index: 3169330 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1828. Min Act: -0.1700
Data Index: 2370468 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1828. Min Act: -0.1700
Data Index: 1831987 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1515. Min Act: -0.1700
Data Index: 5077829 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1515. Min Act: -0.1700
Data Index: 8378224 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1515. Min Act: -0.1700
Data Index: 3093775 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1203. Min Act: -0.1700
Data Index: 7807570 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1203. Min Act: -0.1700
Data Index: 8437573 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1203. Min Act: -0.1700
Data Index: 6469453 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 2669343 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 2783247 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 5096488 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0578. Min Act: -0.1700
Data Index: 8675810 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0578. Min Act: -0.1700
Data Index: 656611 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0578. Min Act: -0.1700
Data Index: 4461869 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19