Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5949 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.4326. Min Act: -0.1700
Data Index: 4054579 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.2764. Min Act: -0.1700
Data Index: 6817533 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.2451. Min Act: -0.1700
Data Index: 6817534 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.2451. Min Act: -0.1700
Data Index: 3237054 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.1514. Min Act: -0.1700
Data Index: 2998659 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.1201. Min Act: -0.1700
Data Index: 8118741 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.1201. Min Act: -0.1700
Data Index: 881153 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.0889. Min Act: -0.1700
Data Index: 978837 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.0576. Min Act: -0.1700
Data Index: 3041296 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.0576. Min Act: -0.1700
Data Index: 3750952 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.0576. Min Act: -0.1700
Data Index: 411684 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.0576. Min Act: -0.1700
Data Index: 4413597 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4326. Min Range: -5.4326
Max Act: 5.0264. Min Act: -0.1700
Data Index: 5667181 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4326. Min Range: -5.4326
Max Act: 4.9326. Min Act: -0.1700
Data Index: 7973756 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4326. Min Range: -5.4326
Max Act: 4.8701. Min Act: -0.1700
Data Index: 609888 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4326. Min Range: -5.4326
Max Act: 4.8389. Min Act: -0.1700
Data Index: 7793991 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4326. Min Range: -5.4326
Max Act: 4.8076. Min Act: -0.1700
Data Index: 2809681 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4326. Min Range: -5.4326
Max Act: 4.8389. Min Act: -0.1700
Data Index: 8604631 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4326. Min Range: -5.4326
Max Act: 4.8076. Min Act: -0.1700
Data Index: 4540245 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4326. Min Range: -5.4326
Max Act: 4.7764. Min Act: -0.1700
Data Index: 6483491 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19