Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0140. Min Range: -7.0140
Max Act: 7.0140. Min Act: -0.1700
Data Index: 4780900 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.9515. Min Act: -0.1700
Data Index: 8128468 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.9515. Min Act: -0.1700
Data Index: 5125014 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.9202. Min Act: -0.1700
Data Index: 8309605 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8577. Min Act: -0.1700
Data Index: 4743110 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8890. Min Act: -0.1700
Data Index: 8683592 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8890. Min Act: -0.1700
Data Index: 7655886 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8577. Min Act: -0.1700
Data Index: 4142533 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8577. Min Act: -0.1700
Data Index: 4185790 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8577. Min Act: -0.1700
Data Index: 4198707 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8577. Min Act: -0.1700
Data Index: 1325682 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8577. Min Act: -0.1700
Data Index: 7379234 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8265. Min Act: -0.1700
Data Index: 3537335 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.7952. Min Act: -0.1700
Data Index: 5563777 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8265. Min Act: -0.1700
Data Index: 2673812 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.8577. Min Act: -0.1700
Data Index: 8196854 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.7952. Min Act: -0.1700
Data Index: 1028390 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.7952. Min Act: -0.1700
Data Index: 616136 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.7952. Min Act: -0.1700
Data Index: 4147183 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0140. Min Range: -7.0140
Max Act: 6.7640. Min Act: -0.1700
Data Index: 5090970 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19