Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.8630. Min Act: -0.1700
Data Index: 1934742 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.8005. Min Act: -0.1700
Data Index: 8265476 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.7380. Min Act: -0.1700
Data Index: 1821156 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.5505. Min Act: -0.1700
Data Index: 2566064 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.1755. Min Act: -0.1700
Data Index: 5962088 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.1130. Min Act: -0.1700
Data Index: 3079928 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.1130. Min Act: -0.1700
Data Index: 970183 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.1130. Min Act: -0.1700
Data Index: 4249298 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.1130. Min Act: -0.1700
Data Index: 2162897 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8630. Min Range: -9.8630
Max Act: 9.0505. Min Act: -0.1700
Data Index: 576893 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9880. Min Act: -0.1700
Data Index: 1614762 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9880. Min Act: -0.1700
Data Index: 4055451 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9255. Min Act: -0.1700
Data Index: 134391 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9880. Min Act: -0.1700
Data Index: 1425566 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9255. Min Act: -0.1700
Data Index: 6534576 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9255. Min Act: -0.1700
Data Index: 1672511 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9255. Min Act: -0.1700
Data Index: 1729523 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9255. Min Act: -0.1700
Data Index: 1535896 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9255. Min Act: -0.1700
Data Index: 7973433 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8630. Min Range: -9.8630
Max Act: 8.9255. Min Act: -0.1700
Data Index: 254071 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19