Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5959 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.8107. Min Act: -0.1700
Data Index: 7657884 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.7795. Min Act: -0.1700
Data Index: 5416183 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.7795. Min Act: -0.1700
Data Index: 1121931 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.7795. Min Act: -0.1700
Data Index: 1684595 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.7482. Min Act: -0.1700
Data Index: 6309920 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.6857. Min Act: -0.1700
Data Index: 8715701 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.6545. Min Act: -0.1700
Data Index: 7956405 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.5607. Min Act: -0.1700
Data Index: 4567594 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.5920. Min Act: -0.1700
Data Index: 3972351 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.5295. Min Act: -0.1700
Data Index: 1187024 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.5295. Min Act: -0.1700
Data Index: 733857 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.5295. Min Act: -0.1700
Data Index: 6573163 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.5295. Min Act: -0.1700
Data Index: 6872357 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.4982. Min Act: -0.1700
Data Index: 1960178 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.4982. Min Act: -0.1700
Data Index: 5845323 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.4670. Min Act: -0.1700
Data Index: 5277939 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.4670. Min Act: -0.1700
Data Index: 8574169 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.4670. Min Act: -0.1700
Data Index: 1255060 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.4357. Min Act: -0.1700
Data Index: 3694520 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8107. Min Range: -5.8107
Max Act: 5.4357. Min Act: -0.1700
Data Index: 847486 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19