Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5369 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.8690. Min Act: -0.1700
Data Index: 4918770 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.4627. Min Act: -0.1700
Data Index: 991173 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2440. Min Act: -0.1700
Data Index: 5384032 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.2127. Min Act: -0.1700
Data Index: 3669711 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.1815. Min Act: -0.1700
Data Index: 1645742 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.1502. Min Act: -0.1700
Data Index: 2380397 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.0877. Min Act: -0.1700
Data Index: 934040 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.1502. Min Act: -0.1700
Data Index: 1676566 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.0877. Min Act: -0.1700
Data Index: 1018271 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.0565. Min Act: -0.1700
Data Index: 6010146 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8690. Min Range: -5.8690
Max Act: 5.0565. Min Act: -0.1700
Data Index: 1488488 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9940. Min Act: -0.1700
Data Index: 5027451 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9940. Min Act: -0.1700
Data Index: 7542914 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9627. Min Act: -0.1700
Data Index: 4903952 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9627. Min Act: -0.1700
Data Index: 1096622 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9627. Min Act: -0.1700
Data Index: 8477509 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9627. Min Act: -0.1700
Data Index: 6999247 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9627. Min Act: -0.1700
Data Index: 8292186 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 2613767 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8690. Min Range: -5.8690
Max Act: 4.9315. Min Act: -0.1700
Data Index: 5846436 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19