Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.4175. Min Act: -0.1617
Data Index: 6118459 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.3822. Min Act: -0.1628
Data Index: 2202938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.3646. Min Act: -0.1621
Data Index: 7508116 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.3293. Min Act: -0.1558
Data Index: 1731252 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.3029. Min Act: -0.1461
Data Index: 4578493 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.3029. Min Act: -0.1683
Data Index: 6191958 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.3029. Min Act: -0.1515
Data Index: 4083802 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2941. Min Act: -0.1447
Data Index: 966323 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2941. Min Act: -0.1635
Data Index: 984698 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2941. Min Act: -0.1655
Data Index: 6055357 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2941. Min Act: -0.1594
Data Index: 209572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2852. Min Act: -0.1635
Data Index: 1690348 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2852. Min Act: -0.1667
Data Index: 2157231 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2764. Min Act: -0.1614
Data Index: 2951771 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2588. Min Act: -0.1498
Data Index: 5972743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2764. Min Act: -0.1527
Data Index: 8069838 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2588. Min Act: -0.1521
Data Index: 5636161 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2588. Min Act: -0.1548
Data Index: 4305394 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2500. Min Act: -0.1398
Data Index: 4621199 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4175. Min Range: -1.4175
Max Act: 1.2235. Min Act: -0.1598
Data Index: 591245 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19