Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6506. Min Range: -8.6506
Max Act: 8.6506. Min Act: -0.1700
Data Index: 8477275 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6506. Min Range: -8.6506
Max Act: 8.3381. Min Act: -0.1700
Data Index: 1729663 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6506. Min Range: -8.6506
Max Act: 8.2756. Min Act: -0.1700
Data Index: 2065809 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6506. Min Range: -8.6506
Max Act: 8.2131. Min Act: -0.1700
Data Index: 2161306 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6506. Min Range: -8.6506
Max Act: 8.1506. Min Act: -0.1700
Data Index: 5792946 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6506. Min Range: -8.6506
Max Act: 8.0881. Min Act: -0.1700
Data Index: 6394037 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6506. Min Range: -8.6506
Max Act: 8.0568. Min Act: -0.1700
Data Index: 4901324 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.9943. Min Act: -0.1700
Data Index: 3820613 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.9943. Min Act: -0.1700
Data Index: 6328084 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.9631. Min Act: -0.1700
Data Index: 5700175 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.9631. Min Act: -0.1700
Data Index: 1395400 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.9318. Min Act: -0.1700
Data Index: 3553961 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.9006. Min Act: -0.1700
Data Index: 1803297 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.8693. Min Act: -0.1700
Data Index: 4697940 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.8693. Min Act: -0.1700
Data Index: 2028852 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.8381. Min Act: -0.1700
Data Index: 774454 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.8381. Min Act: -0.1700
Data Index: 3896446 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.8381. Min Act: -0.1700
Data Index: 3931394 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.8068. Min Act: -0.1700
Data Index: 1339628 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6506. Min Range: -8.6506
Max Act: 7.7756. Min Act: -0.1700
Data Index: 7074457 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19