Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.4429. Min Act: -0.1700
Data Index: 8545866 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.3488. Min Act: -0.1700
Data Index: 4443924 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.3017. Min Act: -0.1700
Data Index: 4144625 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.2232. Min Act: -0.1700
Data Index: 6873864 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.2389. Min Act: -0.1700
Data Index: 7854393 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.2075. Min Act: -0.1700
Data Index: 8641323 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.2075. Min Act: -0.1700
Data Index: 5205362 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.2075. Min Act: -0.1700
Data Index: 8820324 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.2232. Min Act: -0.1700
Data Index: 5126335 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.2075. Min Act: -0.1700
Data Index: 1459787 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1918. Min Act: -0.1700
Data Index: 6120375 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1760. Min Act: -0.1700
Data Index: 814231 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1918. Min Act: -0.1700
Data Index: 5592629 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1603. Min Act: -0.1700
Data Index: 5098095 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1760. Min Act: -0.1700
Data Index: 2712367 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1603. Min Act: -0.1700
Data Index: 203697 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1445. Min Act: -0.1700
Data Index: 4343516 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1288. Min Act: -0.1700
Data Index: 6387021 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1288. Min Act: -0.1700
Data Index: 7912499 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4429. Min Range: -3.4429
Max Act: 3.1603. Min Act: -0.1700
Data Index: 7331509 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19