Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1733 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.7175. Min Act: -0.1700
Data Index: 146518 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.4988. Min Act: -0.1700
Data Index: 4576142 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.4363. Min Act: -0.1700
Data Index: 8525123 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.4050. Min Act: -0.1700
Data Index: 603056 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.3738. Min Act: -0.1700
Data Index: 4408140 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.2488. Min Act: -0.1700
Data Index: 5530211 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.2175. Min Act: -0.1700
Data Index: 7553560 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.2175. Min Act: -0.1700
Data Index: 3333658 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.1550. Min Act: -0.1700
Data Index: 4927752 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.1863. Min Act: -0.1700
Data Index: 1625603 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.1550. Min Act: -0.1700
Data Index: 3499217 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.1550. Min Act: -0.1700
Data Index: 8134629 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.1550. Min Act: -0.1700
Data Index: 1634253 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.1238. Min Act: -0.1700
Data Index: 6125736 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.0613. Min Act: -0.1700
Data Index: 1886354 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.0925. Min Act: -0.1700
Data Index: 7449605 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.0925. Min Act: -0.1700
Data Index: 6112571 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7175. Min Range: -6.7175
Max Act: 6.0613. Min Act: -0.1700
Data Index: 5919930 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7175. Min Range: -6.7175
Max Act: 5.9988. Min Act: -0.1700
Data Index: 5557496 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7175. Min Range: -6.7175
Max Act: 5.9675. Min Act: -0.1700
Data Index: 6431856 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19