Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1284 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.4517. Min Act: -0.1700
Data Index: 1787466 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1704. Min Act: -0.1700
Data Index: 4749271 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1079. Min Act: -0.1700
Data Index: 5344392 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.1079. Min Act: -0.1700
Data Index: 2796866 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.0767. Min Act: -0.1700
Data Index: 2861391 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.9829. Min Act: -0.1700
Data Index: 1978924 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4517. Min Range: -6.4517
Max Act: 6.0142. Min Act: -0.1700
Data Index: 2978243 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.9204. Min Act: -0.1700
Data Index: 8320608 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.9204. Min Act: -0.1700
Data Index: 4150103 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.9204. Min Act: -0.1700
Data Index: 6058866 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.8892. Min Act: -0.1700
Data Index: 4185290 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.9204. Min Act: -0.1700
Data Index: 5549956 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.8892. Min Act: -0.1700
Data Index: 2290303 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.8892. Min Act: -0.1700
Data Index: 1119504 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.8892. Min Act: -0.1700
Data Index: 3131830 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.8267. Min Act: -0.1700
Data Index: 2577945 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.8267. Min Act: -0.1700
Data Index: 609023 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.7954. Min Act: -0.1700
Data Index: 8286144 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.7642. Min Act: -0.1700
Data Index: 522030 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4517. Min Range: -6.4517
Max Act: 5.7954. Min Act: -0.1700
Data Index: 4831480 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19