Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5963 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.6261. Min Act: -0.1664
Data Index: 3798955 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.5779. Min Act: -0.1409
Data Index: 5120101 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.5617. Min Act: -0.1398
Data Index: 7569466 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.5456. Min Act: -0.1293
Data Index: 8345486 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.5456. Min Act: -0.1683
Data Index: 523154 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.5132. Min Act: -0.1620
Data Index: 508374 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.5132. Min Act: -0.1578
Data Index: 1948066 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4971. Min Act: -0.1699
Data Index: 8599238 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4971. Min Act: -0.1214
Data Index: 988428 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4971. Min Act: -0.1699
Data Index: 4651540 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4808. Min Act: -0.1596
Data Index: 177763 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4971. Min Act: -0.1699
Data Index: 3564837 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.5132. Min Act: -0.1670
Data Index: 5356069 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4971. Min Act: -0.1261
Data Index: 910851 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4808. Min Act: -0.1697
Data Index: 952380 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4808. Min Act: -0.1659
Data Index: 7629614 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4808. Min Act: -0.1413
Data Index: 4297773 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4808. Min Act: -0.1444
Data Index: 7392538 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4808. Min Act: -0.1409
Data Index: 7232232 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6261. Min Range: -2.6261
Max Act: 2.4808. Min Act: -0.1570
Data Index: 1332459 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19