Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.2706. Min Act: -0.1700
Data Index: 731058 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.2706. Min Act: -0.1700
Data Index: 7088740 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.1456. Min Act: -0.1700
Data Index: 6838115 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9894. Min Act: -0.1700
Data Index: 1962781 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9894. Min Act: -0.1700
Data Index: 2163474 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9894. Min Act: -0.1700
Data Index: 3744263 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2706. Min Range: -5.2706
Max Act: 5.0206. Min Act: -0.1700
Data Index: 119067 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9581. Min Act: -0.1700
Data Index: 6065091 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9581. Min Act: -0.1700
Data Index: 3088619 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9581. Min Act: -0.1700
Data Index: 6838114 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9269. Min Act: -0.1700
Data Index: 3048700 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8956. Min Act: -0.1700
Data Index: 3481387 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9269. Min Act: -0.1700
Data Index: 5830244 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9269. Min Act: -0.1700
Data Index: 2052124 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8956. Min Act: -0.1700
Data Index: 4289283 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8956. Min Act: -0.1700
Data Index: 659671 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.9269. Min Act: -0.1700
Data Index: 2163463 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8956. Min Act: -0.1700
Data Index: 3239776 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8956. Min Act: -0.1700
Data Index: 6834097 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2706. Min Range: -5.2706
Max Act: 4.8956. Min Act: -0.1700
Data Index: 2814224 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19