Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0342. Min Range: -5.0342
Max Act: 5.0342. Min Act: -0.1700
Data Index: 895163 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.9717. Min Act: -0.1700
Data Index: 8790709 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.9404. Min Act: -0.1700
Data Index: 644712 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.9092. Min Act: -0.1700
Data Index: 2883731 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8467. Min Act: -0.1699
Data Index: 6446060 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8467. Min Act: -0.1699
Data Index: 5391561 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8467. Min Act: -0.1700
Data Index: 7090351 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7842. Min Act: -0.1700
Data Index: 7047213 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.8154. Min Act: -0.1700
Data Index: 7139227 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7529. Min Act: -0.1700
Data Index: 2628737 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7529. Min Act: -0.1700
Data Index: 2950627 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 4723149 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 7915668 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 8452844 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7529. Min Act: -0.1700
Data Index: 32902 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 2110241 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 3743563 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.7217. Min Act: -0.1700
Data Index: 3337993 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.6904. Min Act: -0.1700
Data Index: 2417077 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0342. Min Range: -5.0342
Max Act: 4.6904. Min Act: -0.1700
Data Index: 6935593 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19