Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4204 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3513429 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.6527. Min Act: -0.1700
Data Index: 2437932 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.3714. Min Act: -0.1700
Data Index: 4426218 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.3089. Min Act: -0.1700
Data Index: 2767796 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.2777. Min Act: -0.1700
Data Index: 2483175 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.1839. Min Act: -0.1700
Data Index: 1627656 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.1527. Min Act: -0.1700
Data Index: 5840632 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.1527. Min Act: -0.1700
Data Index: 6778837 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.1214. Min Act: -0.1700
Data Index: 1795158 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.1214. Min Act: -0.1700
Data Index: 3176128 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.0589. Min Act: -0.1700
Data Index: 1841106 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.0277. Min Act: -0.1700
Data Index: 4537893 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.0277. Min Act: -0.1700
Data Index: 8735310 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7464. Min Range: -5.7464
Max Act: 5.0277. Min Act: -0.1700
Data Index: 3753999 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7464. Min Range: -5.7464
Max Act: 4.9652. Min Act: -0.1700
Data Index: 7739648 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7464. Min Range: -5.7464
Max Act: 4.9964. Min Act: -0.1700
Data Index: 2204064 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7464. Min Range: -5.7464
Max Act: 4.9964. Min Act: -0.1700
Data Index: 8554074 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7464. Min Range: -5.7464
Max Act: 4.9652. Min Act: -0.1700
Data Index: 6579000 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7464. Min Range: -5.7464
Max Act: 4.9652. Min Act: -0.1700
Data Index: 3727666 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7464. Min Range: -5.7464
Max Act: 4.9652. Min Act: -0.1700
Data Index: 4633161 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19