Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 661 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2108. Min Range: -5.2108
Max Act: 5.2108. Min Act: -0.1700
Data Index: 4527288 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2108. Min Range: -5.2108
Max Act: 5.1483. Min Act: -0.1700
Data Index: 8261004 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2108. Min Range: -5.2108
Max Act: 5.0546. Min Act: -0.1700
Data Index: 4571182 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2108. Min Range: -5.2108
Max Act: 5.0858. Min Act: -0.1700
Data Index: 7008900 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2108. Min Range: -5.2108
Max Act: 5.0233. Min Act: -0.1700
Data Index: 5907736 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2108. Min Range: -5.2108
Max Act: 5.0233. Min Act: -0.1700
Data Index: 3421258 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9921. Min Act: -0.1700
Data Index: 4539687 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2108. Min Range: -5.2108
Max Act: 5.0233. Min Act: -0.1700
Data Index: 4296142 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9608. Min Act: -0.1700
Data Index: 7067268 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9921. Min Act: -0.1700
Data Index: 5928679 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9608. Min Act: -0.1700
Data Index: 4702764 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9608. Min Act: -0.1700
Data Index: 4747537 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9296. Min Act: -0.1700
Data Index: 5106299 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2536843 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9296. Min Act: -0.1700
Data Index: 1294533 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9296. Min Act: -0.1700
Data Index: 1352950 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9296. Min Act: -0.1700
Data Index: 3245167 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.9296. Min Act: -0.1700
Data Index: 2652332 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.8983. Min Act: -0.1700
Data Index: 5558849 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2108. Min Range: -5.2108
Max Act: 4.8983. Min Act: -0.1700
Data Index: 3924635 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19