Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 860 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0987. Min Range: -6.0987
Max Act: 6.0987. Min Act: -0.1700
Data Index: 2342739 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.8799. Min Act: -0.1700
Data Index: 6181069 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.8487. Min Act: -0.1700
Data Index: 3698891 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.7862. Min Act: -0.1700
Data Index: 756683 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.7862. Min Act: -0.1700
Data Index: 7006597 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.7237. Min Act: -0.1700
Data Index: 366167 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.6612. Min Act: -0.1700
Data Index: 921662 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.6612. Min Act: -0.1700
Data Index: 5438337 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5987. Min Act: -0.1700
Data Index: 3971342 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5674. Min Act: -0.1700
Data Index: 7867817 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5987. Min Act: -0.1700
Data Index: 6450478 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5987. Min Act: -0.1700
Data Index: 3170376 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5362. Min Act: -0.1700
Data Index: 2371999 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5674. Min Act: -0.1700
Data Index: 6717678 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5674. Min Act: -0.1700
Data Index: 4346169 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5362. Min Act: -0.1700
Data Index: 4139465 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5362. Min Act: -0.1700
Data Index: 6490985 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5362. Min Act: -0.1700
Data Index: 4027272 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.5362. Min Act: -0.1700
Data Index: 6959476 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0987. Min Range: -6.0987
Max Act: 5.4737. Min Act: -0.1700
Data Index: 8468560 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19