Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.8874. Min Act: -0.1700
Data Index: 1167656 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.8561. Min Act: -0.1700
Data Index: 2907652 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6999. Min Act: -0.1700
Data Index: 5611880 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6999. Min Act: -0.1700
Data Index: 3046119 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6999. Min Act: -0.1700
Data Index: 2105608 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6686. Min Act: -0.1700
Data Index: 7917183 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6686. Min Act: -0.1700
Data Index: 8130262 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6374. Min Act: -0.1700
Data Index: 1765454 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6686. Min Act: -0.1700
Data Index: 5313330 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6374. Min Act: -0.1700
Data Index: 3471378 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6061. Min Act: -0.1700
Data Index: 5418518 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.6061. Min Act: -0.1700
Data Index: 8410900 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5749. Min Act: -0.1700
Data Index: 3778864 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5436. Min Act: -0.1700
Data Index: 4923745 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5436. Min Act: -0.1700
Data Index: 2198638 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5436. Min Act: -0.1700
Data Index: 7438247 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5436. Min Act: -0.1700
Data Index: 8615654 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5436. Min Act: -0.1700
Data Index: 434512 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5124. Min Act: -0.1700
Data Index: 7916090 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8874. Min Range: -4.8874
Max Act: 4.5124. Min Act: -0.1700
Data Index: 3616370 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19