Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.9842. Min Act: -0.1700
Data Index: 7122947 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.8279. Min Act: -0.1700
Data Index: 8741178 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.7184. Min Act: -0.1700
Data Index: 1526277 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.7341. Min Act: -0.1700
Data Index: 6846222 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.7184. Min Act: -0.1700
Data Index: 7979691 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6715. Min Act: -0.1700
Data Index: 5641088 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6871. Min Act: -0.1700
Data Index: 7049328 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6558. Min Act: -0.1700
Data Index: 7883401 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6715. Min Act: -0.1700
Data Index: 3776327 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6871. Min Act: -0.1700
Data Index: 5802595 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6402. Min Act: -0.1700
Data Index: 3197781 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6402. Min Act: -0.1700
Data Index: 4709765 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6558. Min Act: -0.1700
Data Index: 4820069 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.6715. Min Act: -0.1700
Data Index: 3285740 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.5932. Min Act: -0.1700
Data Index: 1855074 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.5932. Min Act: -0.1700
Data Index: 7995028 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.5932. Min Act: -0.1700
Data Index: 5242121 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.5776. Min Act: -0.1700
Data Index: 1142337 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.5463. Min Act: -0.1700
Data Index: 2386355 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9842. Min Range: -3.9842
Max Act: 3.5932. Min Act: -0.1700
Data Index: 1968482 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19