Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1445. Min Range: -7.1445
Max Act: 7.1445. Min Act: -0.1700
Data Index: 4248842 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1445. Min Range: -7.1445
Max Act: 7.1445. Min Act: -0.1700
Data Index: 1747469 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1445. Min Range: -7.1445
Max Act: 7.1133. Min Act: -0.1700
Data Index: 1340333 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1445. Min Range: -7.1445
Max Act: 7.0820. Min Act: -0.1700
Data Index: 725500 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1445. Min Range: -7.1445
Max Act: 7.0195. Min Act: -0.1700
Data Index: 4933279 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9883. Min Act: -0.1700
Data Index: 5102884 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9570. Min Act: -0.1700
Data Index: 4134365 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9258. Min Act: -0.1700
Data Index: 8004440 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9570. Min Act: -0.1700
Data Index: 2018498 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9570. Min Act: -0.1700
Data Index: 5407613 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9570. Min Act: -0.1700
Data Index: 2691227 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9258. Min Act: -0.1700
Data Index: 302862 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9258. Min Act: -0.1700
Data Index: 2981357 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9258. Min Act: -0.1700
Data Index: 2538202 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.9258. Min Act: -0.1700
Data Index: 3460243 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.8945. Min Act: -0.1700
Data Index: 2819271 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.8945. Min Act: -0.1700
Data Index: 5376868 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.8945. Min Act: -0.1700
Data Index: 7811439 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.8945. Min Act: -0.1700
Data Index: 2335993 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1445. Min Range: -7.1445
Max Act: 6.8945. Min Act: -0.1700
Data Index: 7037376 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19