Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.6682. Min Act: -0.1700
Data Index: 3261693 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.5744. Min Act: -0.1700
Data Index: 2292825 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.5119. Min Act: -0.1700
Data Index: 6985111 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.4182. Min Act: -0.1700
Data Index: 6289582 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.4182. Min Act: -0.1700
Data Index: 5137503 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.3557. Min Act: -0.1700
Data Index: 1814516 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.3244. Min Act: -0.1700
Data Index: 228000 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.3244. Min Act: -0.1700
Data Index: 4623523 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.2619. Min Act: -0.1700
Data Index: 1249109 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.2619. Min Act: -0.1700
Data Index: 1596873 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.2307. Min Act: -0.1700
Data Index: 8758839 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.2619. Min Act: -0.1700
Data Index: 1246386 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.2307. Min Act: -0.1700
Data Index: 211889 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.1994. Min Act: -0.1700
Data Index: 6840413 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.1994. Min Act: -0.1700
Data Index: 6983677 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.1994. Min Act: -0.1700
Data Index: 6568101 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.1369. Min Act: -0.1700
Data Index: 6584978 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.1682. Min Act: -0.1700
Data Index: 1656797 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.1682. Min Act: -0.1700
Data Index: 4672885 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6682. Min Range: -7.6682
Max Act: 7.1369. Min Act: -0.1700
Data Index: 8797453 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19