Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5640 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.4328. Min Act: -0.1700
Data Index: 2066143 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.3078. Min Act: -0.1700
Data Index: 3790377 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.2140. Min Act: -0.1700
Data Index: 5799422 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.1515. Min Act: -0.1700
Data Index: 3524880 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.1203. Min Act: -0.1700
Data Index: 5634400 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.1203. Min Act: -0.1700
Data Index: 1453827 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.0578. Min Act: -0.1700
Data Index: 2626403 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.0578. Min Act: -0.1700
Data Index: 1616043 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9953. Min Act: -0.1700
Data Index: 7392448 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.0265. Min Act: -0.1700
Data Index: 7438061 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.0265. Min Act: -0.1700
Data Index: 16893 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9953. Min Act: -0.1700
Data Index: 8641806 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4328. Min Range: -5.4328
Max Act: 5.0265. Min Act: -0.1700
Data Index: 2225386 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9953. Min Act: -0.1700
Data Index: 4220838 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9953. Min Act: -0.1700
Data Index: 7363408 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9953. Min Act: -0.1700
Data Index: 1479533 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9953. Min Act: -0.1700
Data Index: 1900312 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9953. Min Act: -0.1700
Data Index: 738758 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9328. Min Act: -0.1700
Data Index: 432840 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4328. Min Range: -5.4328
Max Act: 4.9328. Min Act: -0.1700
Data Index: 8051273 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19