Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.9391. Min Act: -0.1700
Data Index: 3076363 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8915. Min Act: -0.1700
Data Index: 2234333 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8757. Min Act: -0.1700
Data Index: 4693693 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8598. Min Act: -0.1700
Data Index: 7236430 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8598. Min Act: -0.1700
Data Index: 640766 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8439. Min Act: -0.1700
Data Index: 6992603 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8280. Min Act: -0.1700
Data Index: 6825977 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8121. Min Act: -0.1700
Data Index: 3410303 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7962. Min Act: -0.1700
Data Index: 2055454 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8121. Min Act: -0.1700
Data Index: 231929 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8121. Min Act: -0.1700
Data Index: 293642 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8121. Min Act: -0.1700
Data Index: 5894209 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7962. Min Act: -0.1700
Data Index: 5657195 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.8121. Min Act: -0.1700
Data Index: 6118741 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7802. Min Act: -0.1700
Data Index: 8291801 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7802. Min Act: -0.1700
Data Index: 4975035 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7802. Min Act: -0.1700
Data Index: 8518985 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7802. Min Act: -0.1700
Data Index: 650580 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7802. Min Act: -0.1700
Data Index: 5851701 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9391. Min Range: -2.9391
Max Act: 2.7643. Min Act: -0.1700
Data Index: 4291912 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19