Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.8132. Min Act: -0.1700
Data Index: 1802149 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.5632. Min Act: -0.1700
Data Index: 6531877 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.5632. Min Act: -0.1700
Data Index: 3059619 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.4382. Min Act: -0.1700
Data Index: 8805952 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.3132. Min Act: -0.1700
Data Index: 7435948 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.3132. Min Act: -0.1700
Data Index: 3844435 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.3132. Min Act: -0.1694
Data Index: 3816224 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.1882. Min Act: -0.1700
Data Index: 6429688 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.1882. Min Act: -0.1700
Data Index: 6429690 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.0632. Min Act: -0.1700
Data Index: 7245229 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.8132. Min Range: -16.8132
Max Act: 16.0632. Min Act: -0.1700
Data Index: 1802151 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.9382. Min Act: -0.1700
Data Index: 6281964 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.9382. Min Act: -0.1700
Data Index: 3844429 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.9382. Min Act: -0.1694
Data Index: 8237229 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.8132. Min Act: -0.1695
Data Index: 5171359 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.8132. Min Act: -0.1700
Data Index: 6288920 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.8132. Min Act: -0.1700
Data Index: 649339 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.8132. Min Act: -0.1700
Data Index: 2738456 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.8132. Min Act: -0.1700
Data Index: 4322389 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.8132. Min Range: -16.8132
Max Act: 15.8132. Min Act: -0.1700
Data Index: 6510670 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19