Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.5280. Min Act: -0.1700
Data Index: 1379075 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.4343. Min Act: -0.1700
Data Index: 1900567 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2780. Min Act: -0.1700
Data Index: 8548778 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2468. Min Act: -0.1700
Data Index: 6956019 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.2468. Min Act: -0.1700
Data Index: 4526566 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5280. Min Range: -5.5280
Max Act: 5.0905. Min Act: -0.1700
Data Index: 1325590 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.9968. Min Act: -0.1700
Data Index: 494879 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.9655. Min Act: -0.1700
Data Index: 1361751 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.9030. Min Act: -0.1700
Data Index: 695017 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.9343. Min Act: -0.1700
Data Index: 4727604 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.9030. Min Act: -0.1700
Data Index: 4113572 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8405. Min Act: -0.1700
Data Index: 1433673 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8718. Min Act: -0.1700
Data Index: 6787163 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8718. Min Act: -0.1700
Data Index: 5920397 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8405. Min Act: -0.1700
Data Index: 8595426 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8405. Min Act: -0.1700
Data Index: 2581784 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8405. Min Act: -0.1700
Data Index: 6787171 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8405. Min Act: -0.1700
Data Index: 7678411 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8405. Min Act: -0.1700
Data Index: 3458135 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5280. Min Range: -5.5280
Max Act: 4.8093. Min Act: -0.1700
Data Index: 7152346 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19