Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.8586. Min Act: -0.1700
Data Index: 2206439 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.8273. Min Act: -0.1700
Data Index: 24194 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.7961. Min Act: -0.1700
Data Index: 6450146 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.7961. Min Act: -0.1700
Data Index: 6551436 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.7648. Min Act: -0.1700
Data Index: 7504357 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.7336. Min Act: -0.1700
Data Index: 4827014 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.7336. Min Act: -0.1700
Data Index: 7140936 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.7336. Min Act: -0.1700
Data Index: 8149678 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.7023. Min Act: -0.1700
Data Index: 8218549 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6711. Min Act: -0.1700
Data Index: 2607221 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6398. Min Act: -0.1700
Data Index: 2756733 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6711. Min Act: -0.1700
Data Index: 4077360 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6398. Min Act: -0.1700
Data Index: 5269964 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6398. Min Act: -0.1700
Data Index: 8111243 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6086. Min Act: -0.1700
Data Index: 3679197 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6086. Min Act: -0.1700
Data Index: 4804983 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6086. Min Act: -0.1700
Data Index: 6244490 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.5773. Min Act: -0.1700
Data Index: 8107778 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6398. Min Act: -0.1700
Data Index: 6287035 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8586. Min Range: -5.8586
Max Act: 5.6086. Min Act: -0.1700
Data Index: 6004280 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19