Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.5408. Min Act: -0.1700
Data Index: 4319230 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.5408. Min Act: -0.1700
Data Index: 1260828 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 4297516 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.5095. Min Act: -0.1700
Data Index: 5459315 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.5095. Min Act: -0.1700
Data Index: 3382355 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.5095. Min Act: -0.1700
Data Index: 2671160 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.5095. Min Act: -0.1700
Data Index: 2841320 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 4549877 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4468. Min Act: -0.1700
Data Index: 4249208 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 654893 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 8536373 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 8278670 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 6856663 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 1916300 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 2520547 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 1555903 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 1445900 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4782. Min Act: -0.1700
Data Index: 4468006 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4468. Min Act: -0.1700
Data Index: 2007253 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5408. Min Range: -3.5408
Max Act: 3.4468. Min Act: -0.1700
Data Index: 4336359 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19