Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.2671. Min Act: -0.1700
Data Index: 7305384 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1728. Min Act: -0.1700
Data Index: 7588389 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1255. Min Act: -0.1700
Data Index: 8365370 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1255. Min Act: -0.1700
Data Index: 2274630 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1098. Min Act: -0.1700
Data Index: 215746 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0783. Min Act: -0.1700
Data Index: 7591636 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0940. Min Act: -0.1700
Data Index: 8821362 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0151. Min Act: -0.1700
Data Index: 2514970 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0151. Min Act: -0.1700
Data Index: 4717051 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9993. Min Act: -0.1700
Data Index: 6971569 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9993. Min Act: -0.1700
Data Index: 8095597 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9677. Min Act: -0.1700
Data Index: 3522234 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9677. Min Act: -0.1700
Data Index: 5724939 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9677. Min Act: -0.1700
Data Index: 1907709 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9519. Min Act: -0.1700
Data Index: 3603565 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9519. Min Act: -0.1700
Data Index: 3008653 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9361. Min Act: -0.1700
Data Index: 5504629 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9044. Min Act: -0.1700
Data Index: 5318221 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9044. Min Act: -0.1700
Data Index: 3603563 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9202. Min Act: -0.1700
Data Index: 8233251 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19