Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2009 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.7530. Min Act: -0.1700
Data Index: 4840803 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.6280. Min Act: -0.1700
Data Index: 1610055 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.5030. Min Act: -0.1700
Data Index: 642128 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.5030. Min Act: -0.1700
Data Index: 8411192 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3780. Min Act: -0.1700
Data Index: 5047418 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3780. Min Act: -0.1700
Data Index: 7499984 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3780. Min Act: -0.1700
Data Index: 784952 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3468. Min Act: -0.1700
Data Index: 644755 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3780. Min Act: -0.1700
Data Index: 5437096 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3468. Min Act: -0.1700
Data Index: 4154178 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3155. Min Act: -0.1700
Data Index: 1367753 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3468. Min Act: -0.1700
Data Index: 715129 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3780. Min Act: -0.1700
Data Index: 2173763 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3155. Min Act: -0.1700
Data Index: 8183900 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3155. Min Act: -0.1700
Data Index: 4922405 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.3155. Min Act: -0.1700
Data Index: 7499985 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.2530. Min Act: -0.1700
Data Index: 2375400 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.2530. Min Act: -0.1700
Data Index: 1795651 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.2843. Min Act: -0.1700
Data Index: 2760428 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7530. Min Range: -5.7530
Max Act: 5.2843. Min Act: -0.1700
Data Index: 6346020 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19