Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.1946. Min Act: -0.1700
Data Index: 7417531 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.1321. Min Act: -0.1700
Data Index: 5970916 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.1009. Min Act: -0.1700
Data Index: 5994894 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.1009. Min Act: -0.1700
Data Index: 10427 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.0696. Min Act: -0.1700
Data Index: 3134430 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.0384. Min Act: -0.1700
Data Index: 1282104 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.9759. Min Act: -0.1700
Data Index: 710590 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.9759. Min Act: -0.1700
Data Index: 4911524 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8821. Min Act: -0.1700
Data Index: 5402844 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 715616 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 3713896 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8196. Min Act: -0.1700
Data Index: 2733761 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8196. Min Act: -0.1700
Data Index: 4750633 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.7884. Min Act: -0.1700
Data Index: 493437 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.7884. Min Act: -0.1700
Data Index: 4942458 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.7884. Min Act: -0.1700
Data Index: 3512234 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.7884. Min Act: -0.1700
Data Index: 2829547 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.7571. Min Act: -0.1700
Data Index: 4550369 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.7571. Min Act: -0.1700
Data Index: 885192 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.7571. Min Act: -0.1700
Data Index: 5905258 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19