Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1457 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.4999. Min Act: -0.1700
Data Index: 234815 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.4686. Min Act: -0.1700
Data Index: 2635611 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.4374. Min Act: -0.1700
Data Index: 7418789 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.4061. Min Act: -0.1700
Data Index: 2696682 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.4061. Min Act: -0.1700
Data Index: 267336 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.3749. Min Act: -0.1700
Data Index: 1679679 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.3124. Min Act: -0.1700
Data Index: 8681574 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.3436. Min Act: -0.1700
Data Index: 8540982 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.3436. Min Act: -0.1700
Data Index: 6038110 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.3436. Min Act: -0.1700
Data Index: 5059503 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.3124. Min Act: -0.1700
Data Index: 6676460 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.2499. Min Act: -0.1700
Data Index: 1012751 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.2186. Min Act: -0.1700
Data Index: 5609719 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.1874. Min Act: -0.1700
Data Index: 5730171 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.2186. Min Act: -0.1700
Data Index: 3364289 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.1874. Min Act: -0.1700
Data Index: 1460982 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.2186. Min Act: -0.1700
Data Index: 2621656 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.1561. Min Act: -0.1700
Data Index: 7018541 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.1561. Min Act: -0.1700
Data Index: 1929150 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4999. Min Range: -5.4999
Max Act: 5.1874. Min Act: -0.1700
Data Index: 4940518 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19