Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 334 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.4335. Min Act: -0.1700
Data Index: 6173915 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3708. Min Act: -0.1700
Data Index: 6398122 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3395. Min Act: -0.1700
Data Index: 7939001 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3395. Min Act: -0.1700
Data Index: 8489762 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3081. Min Act: -0.1700
Data Index: 2715291 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.3081. Min Act: -0.1700
Data Index: 8022082 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2767. Min Act: -0.1700
Data Index: 4934876 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2767. Min Act: -0.1700
Data Index: 5233766 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2453. Min Act: -0.1700
Data Index: 2368851 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2453. Min Act: -0.1700
Data Index: 605197 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2453. Min Act: -0.1700
Data Index: 363192 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2767. Min Act: -0.1700
Data Index: 8333656 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2453. Min Act: -0.1700
Data Index: 8130141 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2138. Min Act: -0.1700
Data Index: 2997978 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2138. Min Act: -0.1700
Data Index: 617861 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2138. Min Act: -0.1700
Data Index: 2807006 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2138. Min Act: -0.1700
Data Index: 2114254 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.1824. Min Act: -0.1700
Data Index: 6039267 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2453. Min Act: -0.1700
Data Index: 2489674 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4335. Min Range: -3.4335
Max Act: 3.2138. Min Act: -0.1700
Data Index: 588016 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19