Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4546 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.5464. Min Act: -0.1700
Data Index: 7713606 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.4526. Min Act: -0.1700
Data Index: 3328037 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.3589. Min Act: -0.1700
Data Index: 7490658 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.3589. Min Act: -0.1700
Data Index: 6125283 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.3589. Min Act: -0.1700
Data Index: 4358528 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2964. Min Act: -0.1700
Data Index: 6125286 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2964. Min Act: -0.1700
Data Index: 6401878 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2339. Min Act: -0.1699
Data Index: 1696217 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2651. Min Act: -0.1700
Data Index: 5925103 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2339. Min Act: -0.1700
Data Index: 4567559 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2651. Min Act: -0.1700
Data Index: 6125287 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2339. Min Act: -0.1700
Data Index: 6125284 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2026. Min Act: -0.1700
Data Index: 4670632 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2339. Min Act: -0.1700
Data Index: 3769679 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.1714. Min Act: -0.1700
Data Index: 2828862 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.2026. Min Act: -0.1700
Data Index: 8055090 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.1714. Min Act: -0.1700
Data Index: 8202085 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.1401. Min Act: -0.1700
Data Index: 8202088 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.1714. Min Act: -0.1700
Data Index: 8202093 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5464. Min Range: -7.5464
Max Act: 7.1714. Min Act: -0.1700
Data Index: 7886121 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19