Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4778 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0232. Min Range: -7.0232
Max Act: 7.0232. Min Act: -0.1700
Data Index: 7497096 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.9607. Min Act: -0.1700
Data Index: 4095072 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.6482. Min Act: -0.1700
Data Index: 1851937 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.5857. Min Act: -0.1700
Data Index: 4506507 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.5857. Min Act: -0.1700
Data Index: 2512940 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.6170. Min Act: -0.1700
Data Index: 207549 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.5857. Min Act: -0.1700
Data Index: 183121 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.5232. Min Act: -0.1700
Data Index: 2306461 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.5232. Min Act: -0.1700
Data Index: 7073838 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4920. Min Act: -0.1700
Data Index: 7137345 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4920. Min Act: -0.1700
Data Index: 2394959 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4607. Min Act: -0.1700
Data Index: 7131 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4295. Min Act: -0.1700
Data Index: 1312852 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4295. Min Act: -0.1700
Data Index: 597040 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4295. Min Act: -0.1700
Data Index: 7595082 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4295. Min Act: -0.1700
Data Index: 1907976 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.3982. Min Act: -0.1700
Data Index: 2025988 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.3982. Min Act: -0.1700
Data Index: 4227758 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.3982. Min Act: -0.1700
Data Index: 3557697 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0232. Min Range: -7.0232
Max Act: 6.4295. Min Act: -0.1700
Data Index: 2750542 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19