Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0261. Min Range: -3.0261
Max Act: 3.0261. Min Act: -0.1700
Data Index: 5931230 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0261. Min Range: -3.0261
Max Act: 3.0261. Min Act: -0.1700
Data Index: 6654047 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0261. Min Range: -3.0261
Max Act: 3.0261. Min Act: -0.1700
Data Index: 5591858 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0261. Min Range: -3.0261
Max Act: 3.0103. Min Act: -0.1700
Data Index: 8378279 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.9787. Min Act: -0.1700
Data Index: 6604924 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8995. Min Act: -0.1700
Data Index: 4972104 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8678. Min Act: -0.1700
Data Index: 6286821 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8836. Min Act: -0.1700
Data Index: 406030 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8678. Min Act: -0.1700
Data Index: 4155526 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8678. Min Act: -0.1700
Data Index: 5952611 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8836. Min Act: -0.1700
Data Index: 4920616 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8678. Min Act: -0.1700
Data Index: 2832696 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8678. Min Act: -0.1700
Data Index: 8043739 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8678. Min Act: -0.1700
Data Index: 3212286 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8678. Min Act: -0.1700
Data Index: 1468669 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8519. Min Act: -0.1700
Data Index: 121399 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8519. Min Act: -0.1700
Data Index: 1198805 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8519. Min Act: -0.1700
Data Index: 6656402 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8360. Min Act: -0.1700
Data Index: 4797941 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0261. Min Range: -3.0261
Max Act: 2.8360. Min Act: -0.1700
Data Index: 4710135 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19