Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2556 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.3927. Min Act: -0.1700
Data Index: 6427423 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.3615. Min Act: -0.1700
Data Index: 4844588 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.2365. Min Act: -0.1700
Data Index: 282691 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3927. Min Range: -6.3927
Max Act: 6.0177. Min Act: -0.1700
Data Index: 1007162 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1027198 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1886887 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9240. Min Act: -0.1700
Data Index: 7497396 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9240. Min Act: -0.1700
Data Index: 70313 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9240. Min Act: -0.1700
Data Index: 1593415 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.9240. Min Act: -0.1700
Data Index: 6147815 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8927. Min Act: -0.1700
Data Index: 8349306 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8615. Min Act: -0.1700
Data Index: 6528827 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.8615. Min Act: -0.1700
Data Index: 5551703 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7677. Min Act: -0.1700
Data Index: 6094050 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7677. Min Act: -0.1700
Data Index: 7751389 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7365. Min Act: -0.1700
Data Index: 800751 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7365. Min Act: -0.1700
Data Index: 5640903 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7365. Min Act: -0.1700
Data Index: 2448969 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7365. Min Act: -0.1700
Data Index: 5508272 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3927. Min Range: -6.3927
Max Act: 5.7365. Min Act: -0.1700
Data Index: 7581752 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19