Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.3183. Min Act: -0.1700
Data Index: 7334689 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.2854. Min Act: -0.1698
Data Index: 8657677 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.2854. Min Act: -0.1700
Data Index: 7569752 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.2359. Min Act: -0.1694
Data Index: 8782933 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.2193. Min Act: -0.1700
Data Index: 1770363 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.2027. Min Act: -0.1700
Data Index: 1895129 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1695. Min Act: -0.1676
Data Index: 3582399 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1695. Min Act: -0.1700
Data Index: 4270737 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1861. Min Act: -0.1694
Data Index: 4220027 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1695. Min Act: -0.1697
Data Index: 111606 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1362. Min Act: -0.1700
Data Index: 7887001 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1362. Min Act: -0.1699
Data Index: 7158996 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1528. Min Act: -0.1700
Data Index: 7256890 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1695. Min Act: -0.1700
Data Index: 7265568 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1528. Min Act: -0.1693
Data Index: 3390737 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1362. Min Act: -0.1698
Data Index: 2708527 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1195. Min Act: -0.1602
Data Index: 4294282 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1195. Min Act: -0.1695
Data Index: 1273872 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1195. Min Act: -0.1699
Data Index: 5335203 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3183. Min Range: -2.3183
Max Act: 2.1027. Min Act: -0.1687
Data Index: 1898518 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19