Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 42 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.2903. Min Act: -0.1700
Data Index: 4876342 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.2590. Min Act: -0.1700
Data Index: 812720 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.2903. Min Act: -0.1700
Data Index: 587686 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.1965. Min Act: -0.1700
Data Index: 5593791 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.1965. Min Act: -0.1700
Data Index: 1529066 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.1340. Min Act: -0.1700
Data Index: 6606238 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.1028. Min Act: -0.1700
Data Index: 761673 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.9778. Min Act: -0.1700
Data Index: 3019307 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.0090. Min Act: -0.1700
Data Index: 3912099 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2903. Min Range: -6.2903
Max Act: 6.0403. Min Act: -0.1700
Data Index: 3364940 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.9778. Min Act: -0.1700
Data Index: 7723911 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.9153. Min Act: -0.1700
Data Index: 2384162 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8840. Min Act: -0.1700
Data Index: 5612646 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8840. Min Act: -0.1700
Data Index: 8063678 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8528. Min Act: -0.1700
Data Index: 5796551 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8840. Min Act: -0.1700
Data Index: 6860461 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8528. Min Act: -0.1700
Data Index: 4534335 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8215. Min Act: -0.1700
Data Index: 7264467 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8215. Min Act: -0.1700
Data Index: 8063086 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2903. Min Range: -6.2903
Max Act: 5.8215. Min Act: -0.1700
Data Index: 3139785 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19