Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0085. Min Range: -6.0085
Max Act: 6.0085. Min Act: -0.1700
Data Index: 3131482 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.9773. Min Act: -0.1700
Data Index: 3722626 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.7898. Min Act: -0.1700
Data Index: 1613854 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6960. Min Act: -0.1700
Data Index: 1858715 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6960. Min Act: -0.1700
Data Index: 7077559 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6648. Min Act: -0.1700
Data Index: 5381090 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6648. Min Act: -0.1700
Data Index: 271188 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6335. Min Act: -0.1700
Data Index: 6748201 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6023. Min Act: -0.1700
Data Index: 8157083 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6023. Min Act: -0.1700
Data Index: 4150781 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6023. Min Act: -0.1700
Data Index: 8150848 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.5398. Min Act: -0.1700
Data Index: 3620702 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.6023. Min Act: -0.1700
Data Index: 1422101 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.5710. Min Act: -0.1700
Data Index: 4165368 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.5398. Min Act: -0.1700
Data Index: 4035881 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.5398. Min Act: -0.1700
Data Index: 1502 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.5085. Min Act: -0.1700
Data Index: 4799528 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.5398. Min Act: -0.1700
Data Index: 4683841 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.5085. Min Act: -0.1700
Data Index: 1375205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0085. Min Range: -6.0085
Max Act: 5.4773. Min Act: -0.1700
Data Index: 3447727 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19