Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3903 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.8490. Min Act: -0.1700
Data Index: 2384210 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.8178. Min Act: -0.1700
Data Index: 2967246 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.7553. Min Act: -0.1700
Data Index: 3163498 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.7553. Min Act: -0.1700
Data Index: 554686 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.6303. Min Act: -0.1700
Data Index: 3019442 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5678. Min Act: -0.1700
Data Index: 6154018 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5678. Min Act: -0.1700
Data Index: 5764222 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5678. Min Act: -0.1700
Data Index: 3648204 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5990. Min Act: -0.1700
Data Index: 4189999 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5678. Min Act: -0.1700
Data Index: 6783029 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5365. Min Act: -0.1700
Data Index: 8587289 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5365. Min Act: -0.1700
Data Index: 3560826 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5678. Min Act: -0.1700
Data Index: 4343694 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5365. Min Act: -0.1700
Data Index: 6452942 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5365. Min Act: -0.1700
Data Index: 1022192 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5365. Min Act: -0.1700
Data Index: 4393761 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5053. Min Act: -0.1700
Data Index: 7413743 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5053. Min Act: -0.1700
Data Index: 7623170 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5053. Min Act: -0.1700
Data Index: 5168447 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8490. Min Range: -5.8490
Max Act: 5.5053. Min Act: -0.1700
Data Index: 6743070 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19