Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2064. Min Range: -6.2064
Max Act: 6.2064. Min Act: -0.1700
Data Index: 8456488 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2064. Min Range: -6.2064
Max Act: 6.0189. Min Act: -0.1700
Data Index: 882869 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2064. Min Range: -6.2064
Max Act: 6.0189. Min Act: -0.1700
Data Index: 5883758 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.9251. Min Act: -0.1700
Data Index: 2044196 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8626. Min Act: -0.1700
Data Index: 4243756 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8939. Min Act: -0.1700
Data Index: 6091575 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8626. Min Act: -0.1700
Data Index: 2612537 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8314. Min Act: -0.1700
Data Index: 1214409 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8314. Min Act: -0.1700
Data Index: 6921869 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8314. Min Act: -0.1700
Data Index: 4827750 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8314. Min Act: -0.1700
Data Index: 4250375 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8001. Min Act: -0.1700
Data Index: 6427435 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8001. Min Act: -0.1700
Data Index: 6309474 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8001. Min Act: -0.1700
Data Index: 5423984 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.8001. Min Act: -0.1700
Data Index: 2612529 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.7689. Min Act: -0.1700
Data Index: 6204962 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.7689. Min Act: -0.1700
Data Index: 2756656 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.7689. Min Act: -0.1700
Data Index: 3218872 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.7376. Min Act: -0.1700
Data Index: 2170572 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2064. Min Range: -6.2064
Max Act: 5.7376. Min Act: -0.1700
Data Index: 1757220 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19