Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4055 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.3705. Min Act: -0.1700
Data Index: 7000605 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.2454. Min Act: -0.1700
Data Index: 1696542 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.2454. Min Act: -0.1700
Data Index: 3505285 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0892. Min Act: -0.1700
Data Index: 7022355 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.1204. Min Act: -0.1700
Data Index: 8679239 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0579. Min Act: -0.1700
Data Index: 6652204 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0579. Min Act: -0.1700
Data Index: 2623572 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0579. Min Act: -0.1700
Data Index: 8694151 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0267. Min Act: -0.1700
Data Index: 5552553 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0267. Min Act: -0.1700
Data Index: 8793642 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0267. Min Act: -0.1700
Data Index: 6031021 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3705. Min Range: -4.3705
Max Act: 4.0267. Min Act: -0.1700
Data Index: 3505286 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9954. Min Act: -0.1700
Data Index: 2106286 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9954. Min Act: -0.1700
Data Index: 8126286 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9641. Min Act: -0.1700
Data Index: 8290331 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9641. Min Act: -0.1700
Data Index: 3128354 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9329. Min Act: -0.1700
Data Index: 3689130 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9641. Min Act: -0.1700
Data Index: 1945192 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9641. Min Act: -0.1700
Data Index: 856090 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3705. Min Range: -4.3705
Max Act: 3.9641. Min Act: -0.1700
Data Index: 4626894 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19