Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.8947. Min Act: -0.1700
Data Index: 6872146 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.6135. Min Act: -0.1700
Data Index: 2060418 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.6135. Min Act: -0.1700
Data Index: 2416483 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.5510. Min Act: -0.1700
Data Index: 5894398 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.4572. Min Act: -0.1700
Data Index: 2885549 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.3947. Min Act: -0.1700
Data Index: 7918604 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.4260. Min Act: -0.1700
Data Index: 8103420 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.3947. Min Act: -0.1700
Data Index: 5590843 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.3322. Min Act: -0.1700
Data Index: 7500584 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.3322. Min Act: -0.1700
Data Index: 175106 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.3322. Min Act: -0.1700
Data Index: 2792068 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2697. Min Act: -0.1700
Data Index: 5320832 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2697. Min Act: -0.1700
Data Index: 578623 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2385. Min Act: -0.1700
Data Index: 4844898 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2385. Min Act: -0.1700
Data Index: 6239468 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2385. Min Act: -0.1700
Data Index: 5382827 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2072. Min Act: -0.1700
Data Index: 6383044 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2072. Min Act: -0.1700
Data Index: 689769 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.2072. Min Act: -0.1700
Data Index: 4252068 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8947. Min Range: -4.8947
Max Act: 4.1759. Min Act: -0.1700
Data Index: 4021484 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19