Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7377. Min Range: -6.7377
Max Act: 6.7377. Min Act: -0.1700
Data Index: 4355260 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7377. Min Range: -6.7377
Max Act: 6.0814. Min Act: -0.1700
Data Index: 5135776 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.9877. Min Act: -0.1700
Data Index: 5101744 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.8002. Min Act: -0.1700
Data Index: 362686 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.6752. Min Act: -0.1700
Data Index: 1685927 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.7064. Min Act: -0.1700
Data Index: 7524478 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.6439. Min Act: -0.1700
Data Index: 1033255 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.6127. Min Act: -0.1700
Data Index: 6999176 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.5189. Min Act: -0.1700
Data Index: 7124178 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.5189. Min Act: -0.1700
Data Index: 429815 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.4877. Min Act: -0.1700
Data Index: 5187485 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.4564. Min Act: -0.1700
Data Index: 3928623 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.4564. Min Act: -0.1700
Data Index: 279415 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.4564. Min Act: -0.1700
Data Index: 1283382 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.5189. Min Act: -0.1700
Data Index: 6572542 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.3939. Min Act: -0.1700
Data Index: 3040183 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.4252. Min Act: -0.1700
Data Index: 1242508 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.4252. Min Act: -0.1700
Data Index: 5549639 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.3627. Min Act: -0.1700
Data Index: 8355519 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7377. Min Range: -6.7377
Max Act: 5.3939. Min Act: -0.1700
Data Index: 3698312 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19