Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3949. Min Range: -7.3949
Max Act: 7.3949. Min Act: -0.1700
Data Index: 2406545 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3949. Min Range: -7.3949
Max Act: 7.2699. Min Act: -0.1700
Data Index: 6061952 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3949. Min Range: -7.3949
Max Act: 7.1136. Min Act: -0.1700
Data Index: 1534273 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3949. Min Range: -7.3949
Max Act: 7.0824. Min Act: -0.1700
Data Index: 601138 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3949. Min Range: -7.3949
Max Act: 7.0511. Min Act: -0.1700
Data Index: 6573436 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3949. Min Range: -7.3949
Max Act: 7.0199. Min Act: -0.1700
Data Index: 3532426 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.9886. Min Act: -0.1700
Data Index: 1683886 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.9261. Min Act: -0.1700
Data Index: 7245200 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.9261. Min Act: -0.1700
Data Index: 4390894 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.9261. Min Act: -0.1700
Data Index: 8466354 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8949. Min Act: -0.1700
Data Index: 5368760 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8636. Min Act: -0.1700
Data Index: 2077709 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8949. Min Act: -0.1700
Data Index: 2046171 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8949. Min Act: -0.1700
Data Index: 5950149 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8636. Min Act: -0.1700
Data Index: 124827 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8636. Min Act: -0.1700
Data Index: 7888162 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8636. Min Act: -0.1700
Data Index: 5670917 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.8011. Min Act: -0.1700
Data Index: 175931 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.7699. Min Act: -0.1700
Data Index: 6222803 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3949. Min Range: -7.3949
Max Act: 6.7386. Min Act: -0.1700
Data Index: 1483602 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19