Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3297. Min Range: -8.3297
Max Act: 8.3297. Min Act: -0.1700
Data Index: 5673819 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.3297. Min Act: -0.1700
Data Index: 8012571 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.3297. Min Act: -0.1700
Data Index: 3307090 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.2359. Min Act: -0.1700
Data Index: 5457817 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.2047. Min Act: -0.1700
Data Index: 5706127 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.2047. Min Act: -0.1700
Data Index: 7516884 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.1422. Min Act: -0.1700
Data Index: 1569905 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.1109. Min Act: -0.1700
Data Index: 6710755 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.0484. Min Act: -0.1700
Data Index: 4926580 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.0172. Min Act: -0.1700
Data Index: 7125844 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.0172. Min Act: -0.1700
Data Index: 6733718 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.9859. Min Act: -0.1700
Data Index: 4262101 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3297. Min Range: -8.3297
Max Act: 7.0172. Min Act: -0.1700
Data Index: 1316333 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.9859. Min Act: -0.1700
Data Index: 3159512 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.9547. Min Act: -0.1700
Data Index: 7111376 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.9547. Min Act: -0.1700
Data Index: 802600 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.9234. Min Act: -0.1700
Data Index: 5094692 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.9234. Min Act: -0.1700
Data Index: 4909373 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.8922. Min Act: -0.1700
Data Index: 611630 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3297. Min Range: -8.3297
Max Act: 6.8922. Min Act: -0.1700
Data Index: 1258667 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19