Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5436 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.4429. Min Act: -0.1700
Data Index: 8024405 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.4429. Min Act: -0.1700
Data Index: 1211751 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.4117. Min Act: -0.1700
Data Index: 2793368 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.3804. Min Act: -0.1700
Data Index: 953367 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.3804. Min Act: -0.1700
Data Index: 2153418 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.3804. Min Act: -0.1700
Data Index: 4756919 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.3492. Min Act: -0.1700
Data Index: 7975159 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.3492. Min Act: -0.1700
Data Index: 3848024 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.3179. Min Act: -0.1700
Data Index: 751476 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.3179. Min Act: -0.1700
Data Index: 1870025 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2867. Min Act: -0.1700
Data Index: 2052635 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2554. Min Act: -0.1700
Data Index: 1765929 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2867. Min Act: -0.1700
Data Index: 6323274 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2867. Min Act: -0.1700
Data Index: 6432623 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2554. Min Act: -0.1700
Data Index: 5294123 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2554. Min Act: -0.1700
Data Index: 2899845 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2554. Min Act: -0.1700
Data Index: 5222706 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2554. Min Act: -0.1700
Data Index: 4468882 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2554. Min Act: -0.1700
Data Index: 2157113 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4429. Min Range: -4.4429
Max Act: 4.2554. Min Act: -0.1700
Data Index: 6124335 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19