Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 865 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7842. Min Range: -8.7842
Max Act: 8.7842. Min Act: -0.1700
Data Index: 8601755 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7842. Min Range: -8.7842
Max Act: 8.0967. Min Act: -0.1700
Data Index: 1157278 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.9717. Min Act: -0.1700
Data Index: 3704669 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.9717. Min Act: -0.1700
Data Index: 1132974 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.9405. Min Act: -0.1700
Data Index: 2538491 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.9405. Min Act: -0.1700
Data Index: 686584 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.9092. Min Act: -0.1700
Data Index: 3788928 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.8780. Min Act: -0.1700
Data Index: 3669921 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.8780. Min Act: -0.1700
Data Index: 4705840 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.8780. Min Act: -0.1700
Data Index: 7727251 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.8155. Min Act: -0.1700
Data Index: 4039204 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.8780. Min Act: -0.1700
Data Index: 8290065 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.8155. Min Act: -0.1700
Data Index: 1324498 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.7842. Min Act: -0.1700
Data Index: 3527913 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.7842. Min Act: -0.1700
Data Index: 1412260 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.7842. Min Act: -0.1700
Data Index: 6835790 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.7217. Min Act: -0.1700
Data Index: 4183046 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.7217. Min Act: -0.1700
Data Index: 28436 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.7217. Min Act: -0.1700
Data Index: 2169465 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7842. Min Range: -8.7842
Max Act: 7.6905. Min Act: -0.1700
Data Index: 5538548 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19