Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2954 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.4773. Min Act: -0.1700
Data Index: 2845212 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3210. Min Act: -0.1700
Data Index: 3832298 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3210. Min Act: -0.1700
Data Index: 5054299 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.3210. Min Act: -0.1700
Data Index: 3014050 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.2898. Min Act: -0.1700
Data Index: 8684980 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1960. Min Act: -0.1700
Data Index: 8752307 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1960. Min Act: -0.1700
Data Index: 8531460 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 5752957 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 6160845 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 8626710 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1648. Min Act: -0.1700
Data Index: 6559262 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1335. Min Act: -0.1700
Data Index: 1360902 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1023. Min Act: -0.1700
Data Index: 7366552 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1335. Min Act: -0.1700
Data Index: 5339459 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1335. Min Act: -0.1700
Data Index: 8709993 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1023. Min Act: -0.1700
Data Index: 516640 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1023. Min Act: -0.1700
Data Index: 3925316 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1023. Min Act: -0.1700
Data Index: 7615593 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1023. Min Act: -0.1700
Data Index: 8548211 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4773. Min Range: -5.4773
Max Act: 5.1023. Min Act: -0.1700
Data Index: 8298096 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19