Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 620 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3675. Min Range: -5.3675
Max Act: 5.3675. Min Act: -0.1700
Data Index: 6502957 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3675. Min Range: -5.3675
Max Act: 5.2425. Min Act: -0.1700
Data Index: 477131 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3675. Min Range: -5.3675
Max Act: 5.2112. Min Act: -0.1700
Data Index: 3020889 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.9612. Min Act: -0.1700
Data Index: 7834655 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.9300. Min Act: -0.1700
Data Index: 3553079 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.9300. Min Act: -0.1700
Data Index: 1565910 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8987. Min Act: -0.1700
Data Index: 5602487 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8987. Min Act: -0.1700
Data Index: 7833529 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8675. Min Act: -0.1700
Data Index: 7020947 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8675. Min Act: -0.1700
Data Index: 5061874 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8362. Min Act: -0.1700
Data Index: 4355918 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8362. Min Act: -0.1700
Data Index: 7936094 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8362. Min Act: -0.1700
Data Index: 6857411 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8362. Min Act: -0.1700
Data Index: 2000477 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8362. Min Act: -0.1700
Data Index: 955228 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8050. Min Act: -0.1700
Data Index: 8666823 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8050. Min Act: -0.1700
Data Index: 6731114 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.8050. Min Act: -0.1700
Data Index: 183673 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.7737. Min Act: -0.1700
Data Index: 1968951 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3675. Min Range: -5.3675
Max Act: 4.7737. Min Act: -0.1700
Data Index: 7200283 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19