Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.9143. Min Act: -0.1700
Data Index: 8776513 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.9143. Min Act: -0.1700
Data Index: 245703 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.8205. Min Act: -0.1700
Data Index: 3160048 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.8048. Min Act: -0.1700
Data Index: 2675181 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.7423. Min Act: -0.1700
Data Index: 4450627 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.7266. Min Act: -0.1700
Data Index: 4012970 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.6484. Min Act: -0.1700
Data Index: 7155324 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.6328. Min Act: -0.1700
Data Index: 1985021 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.6015. Min Act: -0.1700
Data Index: 6699203 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.6171. Min Act: -0.1700
Data Index: 106586 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.6015. Min Act: -0.1700
Data Index: 8526421 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5858. Min Act: -0.1700
Data Index: 4993331 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5545. Min Act: -0.1700
Data Index: 7059313 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5389. Min Act: -0.1700
Data Index: 1554296 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5232. Min Act: -0.1700
Data Index: 19529 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5389. Min Act: -0.1700
Data Index: 639417 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5389. Min Act: -0.1700
Data Index: 2756319 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5232. Min Act: -0.1700
Data Index: 3276700 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5075. Min Act: -0.1700
Data Index: 7138861 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9143. Min Range: -3.9143
Max Act: 3.5075. Min Act: -0.1700
Data Index: 1528008 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19