Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2309 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.8028. Min Act: -0.1700
Data Index: 1184261 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.5528. Min Act: -0.1700
Data Index: 7524381 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.5528. Min Act: -0.1700
Data Index: 7033507 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.5216. Min Act: -0.1700
Data Index: 1018297 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.4903. Min Act: -0.1700
Data Index: 6276521 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.4278. Min Act: -0.1700
Data Index: 3579927 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.3653. Min Act: -0.1700
Data Index: 3762537 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2716. Min Act: -0.1700
Data Index: 6094936 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 901864 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2403. Min Act: -0.1700
Data Index: 1166670 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2403. Min Act: -0.1700
Data Index: 1375722 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2403. Min Act: -0.1700
Data Index: 3182148 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2403. Min Act: -0.1700
Data Index: 988379 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2403. Min Act: -0.1700
Data Index: 4137686 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 5806255 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.1778. Min Act: -0.1700
Data Index: 5771182 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 6276519 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 3214444 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.1778. Min Act: -0.1700
Data Index: 2792609 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8028. Min Range: -5.8028
Max Act: 5.2091. Min Act: -0.1700
Data Index: 5044430 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19