Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1458. Min Range: -8.1458
Max Act: 8.1458. Min Act: -0.1700
Data Index: 1185167 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1458. Min Range: -8.1458
Max Act: 8.0208. Min Act: -0.1700
Data Index: 6401070 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1458. Min Range: -8.1458
Max Act: 8.0208. Min Act: -0.1700
Data Index: 5694383 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1458. Min Range: -8.1458
Max Act: 8.0208. Min Act: -0.1700
Data Index: 2822974 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.9583. Min Act: -0.1700
Data Index: 6294546 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.8958. Min Act: -0.1700
Data Index: 8347296 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.8958. Min Act: -0.1700
Data Index: 1201473 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.8333. Min Act: -0.1700
Data Index: 786059 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.8333. Min Act: -0.1700
Data Index: 3121386 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.8333. Min Act: -0.1700
Data Index: 4929484 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.8333. Min Act: -0.1700
Data Index: 2042844 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7708. Min Act: -0.1700
Data Index: 2739991 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7708. Min Act: -0.1700
Data Index: 7008297 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7708. Min Act: -0.1700
Data Index: 5243158 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7708. Min Act: -0.1700
Data Index: 7113272 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7708. Min Act: -0.1700
Data Index: 3956794 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7708. Min Act: -0.1700
Data Index: 7002288 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7083. Min Act: -0.1700
Data Index: 1850280 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7083. Min Act: -0.1700
Data Index: 2361998 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1458. Min Range: -8.1458
Max Act: 7.7083. Min Act: -0.1700
Data Index: 1405437 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19