Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4060 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0593. Min Range: -6.0593
Max Act: 6.0593. Min Act: -0.1700
Data Index: 4304565 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0593. Min Range: -6.0593
Max Act: 6.0281. Min Act: -0.1700
Data Index: 3411629 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0593. Min Range: -6.0593
Max Act: 6.0281. Min Act: -0.1700
Data Index: 4907866 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.9968. Min Act: -0.1700
Data Index: 396113 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.9656. Min Act: -0.1700
Data Index: 2806311 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.9343. Min Act: -0.1700
Data Index: 239545 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.9343. Min Act: -0.1700
Data Index: 6316868 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.9031. Min Act: -0.1700
Data Index: 3332907 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8718. Min Act: -0.1700
Data Index: 8294404 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8718. Min Act: -0.1700
Data Index: 2957381 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8406. Min Act: -0.1700
Data Index: 6986337 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8406. Min Act: -0.1700
Data Index: 3295978 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8093. Min Act: -0.1700
Data Index: 1294808 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8406. Min Act: -0.1700
Data Index: 2083380 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8406. Min Act: -0.1700
Data Index: 8444811 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8406. Min Act: -0.1700
Data Index: 3050120 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8718. Min Act: -0.1700
Data Index: 2978593 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8406. Min Act: -0.1700
Data Index: 4583005 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8406. Min Act: -0.1700
Data Index: 437511 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0593. Min Range: -6.0593
Max Act: 5.8093. Min Act: -0.1700
Data Index: 1956496 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19