Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.4399. Min Act: -0.1700
Data Index: 1335513 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.4087. Min Act: -0.1700
Data Index: 3346790 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.3774. Min Act: -0.1700
Data Index: 539135 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.3462. Min Act: -0.1700
Data Index: 4179478 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.3462. Min Act: -0.1700
Data Index: 7167645 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.3149. Min Act: -0.1700
Data Index: 7280922 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.2837. Min Act: -0.1700
Data Index: 8380914 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.2837. Min Act: -0.1700
Data Index: 7778793 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.2524. Min Act: -0.1700
Data Index: 2450156 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.2212. Min Act: -0.1700
Data Index: 2999412 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.1899. Min Act: -0.1700
Data Index: 221026 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.2212. Min Act: -0.1700
Data Index: 2859120 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.1587. Min Act: -0.1700
Data Index: 3392022 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.1899. Min Act: -0.1700
Data Index: 1775893 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.1274. Min Act: -0.1700
Data Index: 214693 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.0962. Min Act: -0.1700
Data Index: 4823242 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.0962. Min Act: -0.1700
Data Index: 8572747 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.0337. Min Act: -0.1700
Data Index: 2581399 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.0649. Min Act: -0.1700
Data Index: 2086659 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4399. Min Range: -5.4399
Max Act: 5.0649. Min Act: -0.1700
Data Index: 7829679 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19