Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.5351. Min Act: -0.1700
Data Index: 8596328 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.2851. Min Act: -0.1700
Data Index: 6736008 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.2226. Min Act: -0.1700
Data Index: 519841 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.1601. Min Act: -0.1700
Data Index: 1578878 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4219391 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.1288. Min Act: -0.1700
Data Index: 2785926 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.1288. Min Act: -0.1700
Data Index: 4283661 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.1288. Min Act: -0.1700
Data Index: 1832342 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.0663. Min Act: -0.1700
Data Index: 2438191 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.0351. Min Act: -0.1700
Data Index: 2993967 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.0351. Min Act: -0.1700
Data Index: 785729 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.0038. Min Act: -0.1700
Data Index: 4727600 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.0038. Min Act: -0.1700
Data Index: 2978919 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.0038. Min Act: -0.1700
Data Index: 1644357 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5351. Min Range: -6.5351
Max Act: 6.0038. Min Act: -0.1700
Data Index: 7718181 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5351. Min Range: -6.5351
Max Act: 5.9726. Min Act: -0.1700
Data Index: 5593530 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5351. Min Range: -6.5351
Max Act: 5.9413. Min Act: -0.1700
Data Index: 1111774 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5351. Min Range: -6.5351
Max Act: 5.9413. Min Act: -0.1700
Data Index: 4914760 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5351. Min Range: -6.5351
Max Act: 5.9413. Min Act: -0.1700
Data Index: 7721951 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5351. Min Range: -6.5351
Max Act: 5.9413. Min Act: -0.1700
Data Index: 465845 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19