Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1880 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.3478. Min Act: -0.1700
Data Index: 2645170 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.2693. Min Act: -0.1700
Data Index: 6399163 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.2693. Min Act: -0.1700
Data Index: 2418226 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1908. Min Act: -0.1700
Data Index: 942301 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1908. Min Act: -0.1700
Data Index: 5905603 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1750. Min Act: -0.1700
Data Index: 3555288 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1593. Min Act: -0.1700
Data Index: 1778457 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1750. Min Act: -0.1700
Data Index: 6717913 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1435. Min Act: -0.1700
Data Index: 6893013 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1593. Min Act: -0.1700
Data Index: 8815827 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1435. Min Act: -0.1700
Data Index: 4766859 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1120. Min Act: -0.1700
Data Index: 1160101 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1120. Min Act: -0.1700
Data Index: 6743954 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1120. Min Act: -0.1700
Data Index: 7941671 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.1278. Min Act: -0.1700
Data Index: 5230156 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.0963. Min Act: -0.1700
Data Index: 6872340 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.0963. Min Act: -0.1700
Data Index: 302658 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.0963. Min Act: -0.1700
Data Index: 8222485 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.0805. Min Act: -0.1700
Data Index: 6961129 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3478. Min Range: -3.3478
Max Act: 3.0963. Min Act: -0.1700
Data Index: 7687924 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19