Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4643 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.8119. Min Act: -0.1700
Data Index: 538217 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.7807. Min Act: -0.1700
Data Index: 3923781 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.7494. Min Act: -0.1700
Data Index: 163561 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.7182. Min Act: -0.1700
Data Index: 2713378 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.7182. Min Act: -0.1700
Data Index: 3358869 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.6869. Min Act: -0.1700
Data Index: 6232339 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.7182. Min Act: -0.1700
Data Index: 2708987 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.6869. Min Act: -0.1700
Data Index: 1569600 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.6557. Min Act: -0.1700
Data Index: 4091837 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.6557. Min Act: -0.1700
Data Index: 5561730 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.6244. Min Act: -0.1700
Data Index: 7067850 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.6244. Min Act: -0.1700
Data Index: 4128989 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.5932. Min Act: -0.1700
Data Index: 3358870 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.5932. Min Act: -0.1700
Data Index: 4492730 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.5932. Min Act: -0.1700
Data Index: 2713379 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.5619. Min Act: -0.1700
Data Index: 2603660 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.5932. Min Act: -0.1700
Data Index: 1498282 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.5307. Min Act: -0.1700
Data Index: 2754047 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.5307. Min Act: -0.1700
Data Index: 6643843 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8119. Min Range: -5.8119
Max Act: 5.4994. Min Act: -0.1700
Data Index: 2528868 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19