Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4926 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.7359. Min Act: -0.1700
Data Index: 6397237 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.7359. Min Act: -0.1700
Data Index: 233450 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.6734. Min Act: -0.1700
Data Index: 2350074 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.6109. Min Act: -0.1700
Data Index: 7716654 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.5797. Min Act: -0.1700
Data Index: 1167364 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.5797. Min Act: -0.1700
Data Index: 5923301 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.5484. Min Act: -0.1700
Data Index: 1197388 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.5172. Min Act: -0.1700
Data Index: 4509774 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.5172. Min Act: -0.1700
Data Index: 4430900 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.5172. Min Act: -0.1700
Data Index: 5097062 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4859. Min Act: -0.1700
Data Index: 7042096 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4859. Min Act: -0.1700
Data Index: 421704 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4859. Min Act: -0.1700
Data Index: 2226202 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.5172. Min Act: -0.1700
Data Index: 3326624 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4859. Min Act: -0.1700
Data Index: 139487 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4859. Min Act: -0.1700
Data Index: 8748564 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4547. Min Act: -0.1700
Data Index: 2117230 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4091805 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4547. Min Act: -0.1700
Data Index: 4008439 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7359. Min Range: -5.7359
Max Act: 5.4547. Min Act: -0.1700
Data Index: 3979642 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19