Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.5384. Min Act: -0.1700
Data Index: 1452179 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.3347. Min Act: -0.1700
Data Index: 4903425 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.3504. Min Act: -0.1700
Data Index: 1731324 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.3033. Min Act: -0.1700
Data Index: 4257966 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.3033. Min Act: -0.1700
Data Index: 7033712 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.3033. Min Act: -0.1700
Data Index: 4117108 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.2876. Min Act: -0.1700
Data Index: 376184 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.2719. Min Act: -0.1700
Data Index: 7033711 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.2090. Min Act: -0.1700
Data Index: 1070309 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1933. Min Act: -0.1700
Data Index: 818055 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1933. Min Act: -0.1700
Data Index: 853090 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.2090. Min Act: -0.1700
Data Index: 4303997 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1776. Min Act: -0.1700
Data Index: 6248476 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1776. Min Act: -0.1700
Data Index: 8482366 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1776. Min Act: -0.1700
Data Index: 2508554 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1776. Min Act: -0.1700
Data Index: 3963560 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1618. Min Act: -0.1700
Data Index: 5021233 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1461. Min Act: -0.1700
Data Index: 3660261 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1461. Min Act: -0.1700
Data Index: 681148 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5384. Min Range: -3.5384
Max Act: 3.1461. Min Act: -0.1700
Data Index: 718690 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19