Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1843 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.4756. Min Act: -0.1700
Data Index: 5655557 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.3193. Min Act: -0.1700
Data Index: 3471088 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.2568. Min Act: -0.1700
Data Index: 3837816 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.2256. Min Act: -0.1700
Data Index: 4752196 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.1943. Min Act: -0.1700
Data Index: 6699859 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.1318. Min Act: -0.1700
Data Index: 4106670 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.1631. Min Act: -0.1700
Data Index: 5033968 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.1631. Min Act: -0.1700
Data Index: 5900612 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.1006. Min Act: -0.1700
Data Index: 6681237 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.1006. Min Act: -0.1700
Data Index: 8444748 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0693. Min Act: -0.1700
Data Index: 1365822 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0693. Min Act: -0.1700
Data Index: 4429570 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0693. Min Act: -0.1700
Data Index: 2895167 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0693. Min Act: -0.1700
Data Index: 7034740 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0381. Min Act: -0.1700
Data Index: 5209802 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0381. Min Act: -0.1700
Data Index: 5211163 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0381. Min Act: -0.1700
Data Index: 2248521 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0381. Min Act: -0.1700
Data Index: 80968 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0381. Min Act: -0.1700
Data Index: 208578 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4756. Min Range: -5.4756
Max Act: 5.0381. Min Act: -0.1700
Data Index: 6500209 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19