Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0729. Min Range: -7.0729
Max Act: 7.0729. Min Act: -0.1700
Data Index: 3111484 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0729. Min Range: -7.0729
Max Act: 7.0416. Min Act: -0.1700
Data Index: 6551273 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.9791. Min Act: -0.1700
Data Index: 8091923 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.9166. Min Act: -0.1700
Data Index: 2363312 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.8854. Min Act: -0.1700
Data Index: 2538601 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.8541. Min Act: -0.1700
Data Index: 3842781 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.8229. Min Act: -0.1700
Data Index: 3345000 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.8229. Min Act: -0.1700
Data Index: 6486191 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.7916. Min Act: -0.1700
Data Index: 1781088 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.7916. Min Act: -0.1700
Data Index: 3345001 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.7604. Min Act: -0.1700
Data Index: 102171 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.7604. Min Act: -0.1700
Data Index: 5085918 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.7604. Min Act: -0.1700
Data Index: 3896227 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.6979. Min Act: -0.1700
Data Index: 7044640 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.6666. Min Act: -0.1700
Data Index: 4378396 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.7604. Min Act: -0.1700
Data Index: 2968836 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.7291. Min Act: -0.1700
Data Index: 2407936 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.6666. Min Act: -0.1700
Data Index: 920342 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.6979. Min Act: -0.1700
Data Index: 6431382 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0729. Min Range: -7.0729
Max Act: 6.6979. Min Act: -0.1700
Data Index: 3082933 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19