Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4575. Min Range: -8.4575
Max Act: 8.4575. Min Act: -0.1700
Data Index: 6286970 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4575. Min Range: -8.4575
Max Act: 8.3950. Min Act: -0.1700
Data Index: 5741644 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4575. Min Range: -8.4575
Max Act: 8.2700. Min Act: -0.1700
Data Index: 4225757 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4575. Min Range: -8.4575
Max Act: 8.1450. Min Act: -0.1700
Data Index: 3006645 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4575. Min Range: -8.4575
Max Act: 8.0512. Min Act: -0.1700
Data Index: 4646815 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4575. Min Range: -8.4575
Max Act: 8.0200. Min Act: -0.1700
Data Index: 3980210 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.9887. Min Act: -0.1700
Data Index: 4193008 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.9575. Min Act: -0.1700
Data Index: 6555941 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.8637. Min Act: -0.1700
Data Index: 6024707 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.8637. Min Act: -0.1700
Data Index: 2745216 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.8325. Min Act: -0.1700
Data Index: 7659121 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.7700. Min Act: -0.1700
Data Index: 4695041 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.7700. Min Act: -0.1700
Data Index: 4803971 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.7387. Min Act: -0.1700
Data Index: 6182170 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.7387. Min Act: -0.1700
Data Index: 982301 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.7075. Min Act: -0.1700
Data Index: 5383579 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.7075. Min Act: -0.1700
Data Index: 1437585 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.7075. Min Act: -0.1700
Data Index: 5088406 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.6450. Min Act: -0.1700
Data Index: 5088766 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4575. Min Range: -8.4575
Max Act: 7.6450. Min Act: -0.1700
Data Index: 179487 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19