Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.7903. Min Act: -0.1700
Data Index: 1076804 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.6653. Min Act: -0.1700
Data Index: 4598409 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.5091. Min Act: -0.1700
Data Index: 2570853 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.4466. Min Act: -0.1700
Data Index: 2403219 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.4153. Min Act: -0.1700
Data Index: 7440621 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.4466. Min Act: -0.1700
Data Index: 4131480 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.3216. Min Act: -0.1700
Data Index: 5711130 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.2903. Min Act: -0.1700
Data Index: 3461906 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.2903. Min Act: -0.1700
Data Index: 259697 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.2591. Min Act: -0.1700
Data Index: 262115 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.2591. Min Act: -0.1700
Data Index: 296392 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1966. Min Act: -0.1700
Data Index: 2910420 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1966. Min Act: -0.1700
Data Index: 7013106 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1341. Min Act: -0.1700
Data Index: 7631838 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1341. Min Act: -0.1700
Data Index: 4526812 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1341. Min Act: -0.1700
Data Index: 3198057 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1341. Min Act: -0.1700
Data Index: 7601296 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1653. Min Act: -0.1700
Data Index: 5381231 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.1028. Min Act: -0.1700
Data Index: 5991107 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7903. Min Range: -6.7903
Max Act: 6.0403. Min Act: -0.1700
Data Index: 4088159 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19