Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2296 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1864. Min Range: -8.1864
Max Act: 8.1864. Min Act: -0.1700
Data Index: 5552453 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.9364. Min Act: -0.1700
Data Index: 5901931 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.7489. Min Act: -0.1700
Data Index: 3370153 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.8114. Min Act: -0.1700
Data Index: 4512046 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.7177. Min Act: -0.1700
Data Index: 4035495 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.5302. Min Act: -0.1700
Data Index: 1471301 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.4989. Min Act: -0.1700
Data Index: 2807815 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.4364. Min Act: -0.1700
Data Index: 351255 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.4052. Min Act: -0.1700
Data Index: 2976591 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.3739. Min Act: -0.1700
Data Index: 7528979 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.3739. Min Act: -0.1700
Data Index: 5600598 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.3114. Min Act: -0.1700
Data Index: 690965 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.2802. Min Act: -0.1700
Data Index: 4829932 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.2802. Min Act: -0.1700
Data Index: 1542301 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.2802. Min Act: -0.1700
Data Index: 8534439 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.2489. Min Act: -0.1700
Data Index: 4554305 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.2177. Min Act: -0.1700
Data Index: 6096242 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.2177. Min Act: -0.1700
Data Index: 1749693 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.1864. Min Act: -0.1700
Data Index: 3267055 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1864. Min Range: -8.1864
Max Act: 7.1864. Min Act: -0.1700
Data Index: 7029501 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19