Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.9520. Min Act: -0.1700
Data Index: 889819 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.7332. Min Act: -0.1700
Data Index: 111095 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.7332. Min Act: -0.1700
Data Index: 4250147 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.7020. Min Act: -0.1700
Data Index: 841283 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.7020. Min Act: -0.1700
Data Index: 1406544 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.7020. Min Act: -0.1700
Data Index: 2291244 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.6707. Min Act: -0.1700
Data Index: 2302254 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.6707. Min Act: -0.1700
Data Index: 8624880 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.6395. Min Act: -0.1700
Data Index: 8460539 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.6395. Min Act: -0.1700
Data Index: 2132807 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.6082. Min Act: -0.1700
Data Index: 8457452 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5770. Min Act: -0.1700
Data Index: 4797877 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5770. Min Act: -0.1700
Data Index: 5470429 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5770. Min Act: -0.1700
Data Index: 5582931 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5770. Min Act: -0.1700
Data Index: 980861 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5457. Min Act: -0.1700
Data Index: 4592372 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5770. Min Act: -0.1700
Data Index: 3115031 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5457. Min Act: -0.1700
Data Index: 6076401 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5145. Min Act: -0.1700
Data Index: 97352 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9520. Min Range: -4.9520
Max Act: 4.5145. Min Act: -0.1700
Data Index: 4388874 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19