Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0078. Min Range: -9.0078
Max Act: 9.0078. Min Act: -0.1700
Data Index: 1768007 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.8203. Min Act: -0.1700
Data Index: 4638188 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.6953. Min Act: -0.1700
Data Index: 1449406 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.4453. Min Act: -0.1700
Data Index: 6771895 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.3203. Min Act: -0.1700
Data Index: 5792692 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.3203. Min Act: -0.1700
Data Index: 8458997 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.2578. Min Act: -0.1700
Data Index: 4612350 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.1328. Min Act: -0.1700
Data Index: 2747788 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.1328. Min Act: -0.1700
Data Index: 2815656 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.1328. Min Act: -0.1700
Data Index: 7822199 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.0703. Min Act: -0.1700
Data Index: 5461165 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.0703. Min Act: -0.1700
Data Index: 7745648 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.0703. Min Act: -0.1700
Data Index: 8265859 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0078. Min Range: -9.0078
Max Act: 8.0078. Min Act: -0.1700
Data Index: 2167745 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0078. Min Range: -9.0078
Max Act: 7.9453. Min Act: -0.1700
Data Index: 6727399 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0078. Min Range: -9.0078
Max Act: 7.8828. Min Act: -0.1700
Data Index: 6900526 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0078. Min Range: -9.0078
Max Act: 7.9453. Min Act: -0.1700
Data Index: 5405142 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0078. Min Range: -9.0078
Max Act: 7.9453. Min Act: -0.1700
Data Index: 3647142 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0078. Min Range: -9.0078
Max Act: 7.9453. Min Act: -0.1700
Data Index: 3299085 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0078. Min Range: -9.0078
Max Act: 7.8828. Min Act: -0.1700
Data Index: 5733437 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19