Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0382. Min Range: -2.0382
Max Act: 2.0382. Min Act: -0.1700
Data Index: 8461170 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0382. Min Range: -2.0382
Max Act: 2.0044. Min Act: -0.1700
Data Index: 3114437 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9875. Min Act: -0.1700
Data Index: 1939390 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9706. Min Act: -0.1700
Data Index: 580394 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9706. Min Act: -0.1700
Data Index: 3595954 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 5528999 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 4676427 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1697
Data Index: 7095338 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 6574582 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 6478939 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9536. Min Act: -0.1700
Data Index: 2075759 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 2029274 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9196. Min Act: -0.1699
Data Index: 6515516 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 1329868 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9196. Min Act: -0.1700
Data Index: 3347000 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9196. Min Act: -0.1700
Data Index: 7018635 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9026. Min Act: -0.1700
Data Index: 805638 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9196. Min Act: -0.1700
Data Index: 176241 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 3041370 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0382. Min Range: -2.0382
Max Act: 1.9366. Min Act: -0.1700
Data Index: 7943083 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19