Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 830 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.4820. Min Act: -0.1700
Data Index: 3739691 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.3844. Min Act: -0.1700
Data Index: 686475 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.3353. Min Act: -0.1700
Data Index: 6455763 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.3188. Min Act: -0.1700
Data Index: 8664361 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.3188. Min Act: -0.1700
Data Index: 4209323 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2695. Min Act: -0.1700
Data Index: 163060 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2859. Min Act: -0.1700
Data Index: 4662720 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2529. Min Act: -0.1700
Data Index: 5156875 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2695. Min Act: -0.1700
Data Index: 4809846 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2529. Min Act: -0.1700
Data Index: 8461361 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2695. Min Act: -0.1700
Data Index: 8737425 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2529. Min Act: -0.1699
Data Index: 685037 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2364. Min Act: -0.1700
Data Index: 1556132 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2529. Min Act: -0.1700
Data Index: 805139 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2199. Min Act: -0.1700
Data Index: 5187226 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2364. Min Act: -0.1700
Data Index: 6906670 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2364. Min Act: -0.1700
Data Index: 638799 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2364. Min Act: -0.1700
Data Index: 3094658 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2529. Min Act: -0.1700
Data Index: 4741019 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4820. Min Range: -2.4820
Max Act: 2.2364. Min Act: -0.1700
Data Index: 5119122 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19