Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.3765. Min Act: -0.1700
Data Index: 8100923 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.2827. Min Act: -0.1700
Data Index: 7420518 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.2202. Min Act: -0.1700
Data Index: 2450785 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.2202. Min Act: -0.1700
Data Index: 3287009 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.1890. Min Act: -0.1700
Data Index: 6706080 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3131440 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.0952. Min Act: -0.1700
Data Index: 1303513 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.1265. Min Act: -0.1700
Data Index: 3823451 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.0640. Min Act: -0.1700
Data Index: 5788494 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.0327. Min Act: -0.1700
Data Index: 1441561 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3765. Min Range: -5.3765
Max Act: 5.0015. Min Act: -0.1700
Data Index: 1223300 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.9390. Min Act: -0.1700
Data Index: 4940912 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.9390. Min Act: -0.1700
Data Index: 2353685 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.9077. Min Act: -0.1700
Data Index: 758465 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.9077. Min Act: -0.1700
Data Index: 3439747 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.8765. Min Act: -0.1700
Data Index: 8116790 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.8765. Min Act: -0.1700
Data Index: 929742 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.8140. Min Act: -0.1700
Data Index: 1938909 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.8452. Min Act: -0.1700
Data Index: 6740185 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3765. Min Range: -5.3765
Max Act: 4.8452. Min Act: -0.1700
Data Index: 3477001 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19