Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1523. Min Range: -8.1523
Max Act: 8.1523. Min Act: -0.1700
Data Index: 2867247 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1523. Min Range: -8.1523
Max Act: 8.0273. Min Act: -0.1700
Data Index: 2653790 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.7148. Min Act: -0.1700
Data Index: 2457768 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.7148. Min Act: -0.1700
Data Index: 634278 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.6836. Min Act: -0.1700
Data Index: 4311820 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.6523. Min Act: -0.1700
Data Index: 5214108 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.6523. Min Act: -0.1700
Data Index: 5021455 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.6523. Min Act: -0.1700
Data Index: 3464080 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.6211. Min Act: -0.1700
Data Index: 495929 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.6523. Min Act: -0.1700
Data Index: 4855326 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.6211. Min Act: -0.1700
Data Index: 7143767 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.5273. Min Act: -0.1700
Data Index: 892889 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.5273. Min Act: -0.1700
Data Index: 8410771 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.5586. Min Act: -0.1700
Data Index: 4067159 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.4961. Min Act: -0.1700
Data Index: 7483863 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.4961. Min Act: -0.1700
Data Index: 2896582 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.4961. Min Act: -0.1700
Data Index: 7227517 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.4961. Min Act: -0.1700
Data Index: 5298042 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.5273. Min Act: -0.1700
Data Index: 3699714 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1523. Min Range: -8.1523
Max Act: 7.4648. Min Act: -0.1700
Data Index: 2059543 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19