Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2162 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.8923. Min Act: -0.1700
Data Index: 6039745 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.7673. Min Act: -0.1700
Data Index: 2205289 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.6423. Min Act: -0.1700
Data Index: 5052560 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.6423. Min Act: -0.1700
Data Index: 1864611 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.6423. Min Act: -0.1700
Data Index: 114071 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.6110. Min Act: -0.1700
Data Index: 6454693 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5798. Min Act: -0.1700
Data Index: 8159332 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5485. Min Act: -0.1700
Data Index: 2806145 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5798. Min Act: -0.1700
Data Index: 3871621 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5485. Min Act: -0.1700
Data Index: 599337 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5485. Min Act: -0.1700
Data Index: 2254660 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5485. Min Act: -0.1700
Data Index: 8612901 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5485. Min Act: -0.1700
Data Index: 3045055 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5173. Min Act: -0.1700
Data Index: 8087518 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5173. Min Act: -0.1700
Data Index: 3007832 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.5173. Min Act: -0.1700
Data Index: 194158 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.4860. Min Act: -0.1700
Data Index: 961586 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.4860. Min Act: -0.1700
Data Index: 4983252 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.4860. Min Act: -0.1700
Data Index: 230341 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8923. Min Range: -5.8923
Max Act: 5.4860. Min Act: -0.1700
Data Index: 1419830 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19