Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4444 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0783. Min Range: -6.0783
Max Act: 6.0783. Min Act: -0.1700
Data Index: 2276605 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0783. Min Range: -6.0783
Max Act: 6.0158. Min Act: -0.1700
Data Index: 1451273 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0783. Min Range: -6.0783
Max Act: 6.0158. Min Act: -0.1700
Data Index: 7234504 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0783. Min Range: -6.0783
Max Act: 6.0158. Min Act: -0.1700
Data Index: 6431358 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9846. Min Act: -0.1700
Data Index: 4935119 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9846. Min Act: -0.1700
Data Index: 1162320 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9533. Min Act: -0.1700
Data Index: 3841243 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9533. Min Act: -0.1700
Data Index: 1686974 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9533. Min Act: -0.1700
Data Index: 1436985 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9533. Min Act: -0.1700
Data Index: 825332 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6379007 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.9221. Min Act: -0.1700
Data Index: 5100144 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8908. Min Act: -0.1700
Data Index: 4279693 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8908. Min Act: -0.1700
Data Index: 1198057 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8596. Min Act: -0.1700
Data Index: 4818216 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8596. Min Act: -0.1700
Data Index: 1292659 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8596. Min Act: -0.1700
Data Index: 3816175 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8283. Min Act: -0.1700
Data Index: 2462973 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8283. Min Act: -0.1700
Data Index: 2154185 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0783. Min Range: -6.0783
Max Act: 5.8283. Min Act: -0.1700
Data Index: 1180650 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19