Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.7902. Min Act: -0.1700
Data Index: 2267367 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.4777. Min Act: -0.1700
Data Index: 1469332 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.4152. Min Act: -0.1700
Data Index: 4298835 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.4152. Min Act: -0.1700
Data Index: 2614159 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.3527. Min Act: -0.1700
Data Index: 3246194 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.3839. Min Act: -0.1700
Data Index: 5611195 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.3527. Min Act: -0.1700
Data Index: 5687974 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.3839. Min Act: -0.1700
Data Index: 1543220 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.3214. Min Act: -0.1700
Data Index: 891465 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.3214. Min Act: -0.1700
Data Index: 4298849 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.2902. Min Act: -0.1700
Data Index: 1337860 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.2277. Min Act: -0.1700
Data Index: 3797940 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.2589. Min Act: -0.1700
Data Index: 6834612 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.1964. Min Act: -0.1700
Data Index: 5207627 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.2277. Min Act: -0.1700
Data Index: 2699254 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.2277. Min Act: -0.1700
Data Index: 3681507 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.2589. Min Act: -0.1700
Data Index: 4358705 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.1652. Min Act: -0.1700
Data Index: 7197252 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.1339. Min Act: -0.1700
Data Index: 5927996 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7902. Min Range: -6.7902
Max Act: 6.1339. Min Act: -0.1700
Data Index: 4206407 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19