Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.3222. Min Act: -0.1700
Data Index: 3230460 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.2597. Min Act: -0.1700
Data Index: 2065106 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.2284. Min Act: -0.1700
Data Index: 5921803 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1972. Min Act: -0.1700
Data Index: 1127785 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.2284. Min Act: -0.1700
Data Index: 120450 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.2284. Min Act: -0.1700
Data Index: 5367759 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.2284. Min Act: -0.1700
Data Index: 5319053 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1972. Min Act: -0.1700
Data Index: 1729952 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1972. Min Act: -0.1700
Data Index: 892173 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1659. Min Act: -0.1700
Data Index: 7020142 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1346. Min Act: -0.1700
Data Index: 2814934 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1659. Min Act: -0.1700
Data Index: 1783217 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1659. Min Act: -0.1700
Data Index: 2813116 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1972. Min Act: -0.1700
Data Index: 7399935 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1659. Min Act: -0.1700
Data Index: 4191678 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1346. Min Act: -0.1700
Data Index: 255103 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1659. Min Act: -0.1700
Data Index: 3642074 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1346. Min Act: -0.1700
Data Index: 75571 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1659. Min Act: -0.1700
Data Index: 6090100 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3222. Min Range: -4.3222
Max Act: 4.1346. Min Act: -0.1700
Data Index: 6913304 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19