Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1411 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0795. Min Act: -0.1700
Data Index: 422958 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0482. Min Act: -0.1700
Data Index: 2991668 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0482. Min Act: -0.1700
Data Index: 5189303 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0170. Min Act: -0.1700
Data Index: 7659914 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0482. Min Act: -0.1700
Data Index: 2012727 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0170. Min Act: -0.1700
Data Index: 1411167 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0795. Min Range: -6.0795
Max Act: 6.0170. Min Act: -0.1700
Data Index: 2266754 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.9857. Min Act: -0.1700
Data Index: 1346704 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.9545. Min Act: -0.1700
Data Index: 1346702 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.9545. Min Act: -0.1700
Data Index: 1346705 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.9232. Min Act: -0.1700
Data Index: 5342414 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8295. Min Act: -0.1700
Data Index: 1346709 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8607. Min Act: -0.1700
Data Index: 7475263 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8607. Min Act: -0.1700
Data Index: 6120357 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8607. Min Act: -0.1700
Data Index: 1346706 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8607. Min Act: -0.1700
Data Index: 2219955 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8295. Min Act: -0.1700
Data Index: 3731887 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8295. Min Act: -0.1700
Data Index: 7336329 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8295. Min Act: -0.1700
Data Index: 4537824 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0795. Min Range: -6.0795
Max Act: 5.8295. Min Act: -0.1700
Data Index: 1346708 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19