Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3827 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.3821. Min Act: -0.1700
Data Index: 3949909 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.4134. Min Act: -0.1700
Data Index: 7010322 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.1634. Min Act: -0.1700
Data Index: 4354555 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.1009. Min Act: -0.1700
Data Index: 6446571 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.1009. Min Act: -0.1700
Data Index: 4602990 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.1946. Min Act: -0.1700
Data Index: 2671861 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.1009. Min Act: -0.1700
Data Index: 3743202 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.0696. Min Act: -0.1700
Data Index: 1138883 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.0696. Min Act: -0.1700
Data Index: 5480064 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4134. Min Range: -7.4134
Max Act: 7.0384. Min Act: -0.1700
Data Index: 5522575 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9446. Min Act: -0.1700
Data Index: 8737541 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9134. Min Act: -0.1700
Data Index: 894266 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9446. Min Act: -0.1700
Data Index: 1770923 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9134. Min Act: -0.1700
Data Index: 5576000 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8821. Min Act: -0.1700
Data Index: 1615903 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.9134. Min Act: -0.1700
Data Index: 4765266 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 3852872 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 5009738 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.8509. Min Act: -0.1700
Data Index: 5316570 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4134. Min Range: -7.4134
Max Act: 6.7884. Min Act: -0.1700
Data Index: 4839598 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19