Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0065. Min Range: -6.0065
Max Act: 6.0065. Min Act: -0.1700
Data Index: 3927762 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0065. Min Range: -6.0065
Max Act: 6.0065. Min Act: -0.1700
Data Index: 5340352 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.9128. Min Act: -0.1700
Data Index: 4237374 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.9128. Min Act: -0.1700
Data Index: 525594 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.8815. Min Act: -0.1700
Data Index: 4598539 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.8503. Min Act: -0.1700
Data Index: 1007132 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.8503. Min Act: -0.1700
Data Index: 5982078 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.7565. Min Act: -0.1700
Data Index: 5120115 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.7253. Min Act: -0.1700
Data Index: 120561 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.6628. Min Act: -0.1700
Data Index: 5721270 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.6628. Min Act: -0.1700
Data Index: 8634632 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.6315. Min Act: -0.1700
Data Index: 7570656 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.6003. Min Act: -0.1700
Data Index: 232408 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.6003. Min Act: -0.1700
Data Index: 2256236 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.5690. Min Act: -0.1700
Data Index: 3498699 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.5690. Min Act: -0.1700
Data Index: 5165040 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.5378. Min Act: -0.1700
Data Index: 1427659 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.5378. Min Act: -0.1700
Data Index: 5763991 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.5378. Min Act: -0.1700
Data Index: 1276566 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0065. Min Range: -6.0065
Max Act: 5.5378. Min Act: -0.1700
Data Index: 2224078 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19