Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3899 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0418. Min Range: -8.0418
Max Act: 8.0418. Min Act: -0.1700
Data Index: 7729109 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.8230. Min Act: -0.1700
Data Index: 7642503 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.7605. Min Act: -0.1700
Data Index: 6510886 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.6355. Min Act: -0.1700
Data Index: 7575651 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.5105. Min Act: -0.1700
Data Index: 3340449 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.5418. Min Act: -0.1700
Data Index: 8525947 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.4793. Min Act: -0.1700
Data Index: 5860821 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.4168. Min Act: -0.1700
Data Index: 2757403 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.3855. Min Act: -0.1700
Data Index: 1296410 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.3543. Min Act: -0.1700
Data Index: 1338536 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.3855. Min Act: -0.1700
Data Index: 7077171 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.3543. Min Act: -0.1700
Data Index: 1933619 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.3543. Min Act: -0.1700
Data Index: 6153240 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.3543. Min Act: -0.1700
Data Index: 2693352 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.2918. Min Act: -0.1700
Data Index: 1218624 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.2918. Min Act: -0.1700
Data Index: 4321001 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.2605. Min Act: -0.1700
Data Index: 4877604 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.2293. Min Act: -0.1700
Data Index: 1076662 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.1980. Min Act: -0.1700
Data Index: 8153791 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0418. Min Range: -8.0418
Max Act: 7.2293. Min Act: -0.1700
Data Index: 2976266 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19