Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0744. Min Range: -5.0744
Max Act: 5.0744. Min Act: -0.1700
Data Index: 4299932 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0744. Min Range: -5.0744
Max Act: 5.0431. Min Act: -0.1700
Data Index: 4099264 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0744. Min Range: -5.0744
Max Act: 5.0431. Min Act: -0.1700
Data Index: 1085009 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.9494. Min Act: -0.1700
Data Index: 6707445 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.9494. Min Act: -0.1700
Data Index: 566560 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.9494. Min Act: -0.1700
Data Index: 6216503 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.9181. Min Act: -0.1700
Data Index: 5027682 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.9181. Min Act: -0.1700
Data Index: 2957450 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.9181. Min Act: -0.1700
Data Index: 8217468 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.9181. Min Act: -0.1700
Data Index: 2072752 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8869. Min Act: -0.1700
Data Index: 7000015 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8869. Min Act: -0.1700
Data Index: 1413080 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8556. Min Act: -0.1700
Data Index: 8722988 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8556. Min Act: -0.1700
Data Index: 4955499 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8556. Min Act: -0.1700
Data Index: 3271850 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8556. Min Act: -0.1700
Data Index: 8582762 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8244. Min Act: -0.1700
Data Index: 6670872 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.8244. Min Act: -0.1700
Data Index: 4005954 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.7931. Min Act: -0.1700
Data Index: 7652366 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0744. Min Range: -5.0744
Max Act: 4.7931. Min Act: -0.1700
Data Index: 2696993 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19