Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2832 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0142. Min Range: -7.0142
Max Act: 7.0142. Min Act: -0.1700
Data Index: 8458320 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.9517. Min Act: -0.1700
Data Index: 1135787 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.6705. Min Act: -0.1700
Data Index: 3988578 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.6080. Min Act: -0.1700
Data Index: 7718419 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.5767. Min Act: -0.1700
Data Index: 7972397 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.4830. Min Act: -0.1700
Data Index: 2223682 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.4517. Min Act: -0.1700
Data Index: 8828632 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.4517. Min Act: -0.1700
Data Index: 2639063 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.4517. Min Act: -0.1700
Data Index: 4890816 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.4205. Min Act: -0.1700
Data Index: 7790726 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.4517. Min Act: -0.1700
Data Index: 1410073 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3892. Min Act: -0.1700
Data Index: 779622 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3892. Min Act: -0.1700
Data Index: 1504828 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3892. Min Act: -0.1700
Data Index: 4882663 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3892. Min Act: -0.1700
Data Index: 2605377 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3580. Min Act: -0.1700
Data Index: 3922706 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3267. Min Act: -0.1700
Data Index: 3354387 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3267. Min Act: -0.1700
Data Index: 3109682 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.3267. Min Act: -0.1700
Data Index: 7237895 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0142. Min Range: -7.0142
Max Act: 6.2955. Min Act: -0.1700
Data Index: 2689930 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19