Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.4814. Min Act: -0.1700
Data Index: 7210353 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.5127. Min Act: -0.1700
Data Index: 3412821 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.4502. Min Act: -0.1700
Data Index: 6949320 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3876. Min Act: -0.1700
Data Index: 1165358 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3876. Min Act: -0.1700
Data Index: 4908983 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3876. Min Act: -0.1700
Data Index: 5139266 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3876. Min Act: -0.1700
Data Index: 114426 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3564. Min Act: -0.1700
Data Index: 4054652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3564. Min Act: -0.1700
Data Index: 6424641 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3564. Min Act: -0.1700
Data Index: 6687047 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3251. Min Act: -0.1700
Data Index: 1993893 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.3251. Min Act: -0.1700
Data Index: 7575840 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2939. Min Act: -0.1700
Data Index: 4370266 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2939. Min Act: -0.1700
Data Index: 2463965 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2626. Min Act: -0.1700
Data Index: 8546251 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2939. Min Act: -0.1700
Data Index: 5655112 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2939. Min Act: -0.1700
Data Index: 198417 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2939. Min Act: -0.1700
Data Index: 1086792 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2939. Min Act: -0.1700
Data Index: 2379953 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5127. Min Range: -4.5127
Max Act: 4.2626. Min Act: -0.1700
Data Index: 6687045 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19