Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.9569. Min Act: -0.1700
Data Index: 2737138 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.9569. Min Act: -0.1700
Data Index: 7354293 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.8632. Min Act: -0.1700
Data Index: 998788 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.8319. Min Act: -0.1700
Data Index: 6713732 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.8007. Min Act: -0.1700
Data Index: 6373641 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.8007. Min Act: -0.1700
Data Index: 2129969 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.7382. Min Act: -0.1700
Data Index: 7417965 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.7069. Min Act: -0.1700
Data Index: 8691443 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.7069. Min Act: -0.1700
Data Index: 792492 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.6757. Min Act: -0.1700
Data Index: 5745354 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.6757. Min Act: -0.1700
Data Index: 7921763 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.6444. Min Act: -0.1700
Data Index: 1490211 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.6444. Min Act: -0.1700
Data Index: 2402684 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.5819. Min Act: -0.1700
Data Index: 6141389 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.6132. Min Act: -0.1700
Data Index: 3891319 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.5819. Min Act: -0.1700
Data Index: 2397951 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.5819. Min Act: -0.1700
Data Index: 5216336 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.5819. Min Act: -0.1700
Data Index: 144829 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.6132. Min Act: -0.1700
Data Index: 117768 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9569. Min Range: -4.9569
Max Act: 4.5507. Min Act: -0.1700
Data Index: 7432272 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19