Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4884 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2300. Min Range: -6.2300
Max Act: 6.2300. Min Act: -0.1700
Data Index: 1100233 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2300. Min Range: -6.2300
Max Act: 6.0425. Min Act: -0.1700
Data Index: 5003320 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2300. Min Range: -6.2300
Max Act: 6.0738. Min Act: -0.1700
Data Index: 5464000 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2300. Min Range: -6.2300
Max Act: 6.0425. Min Act: -0.1700
Data Index: 6003451 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2300. Min Range: -6.2300
Max Act: 6.0425. Min Act: -0.1700
Data Index: 8666144 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.9488. Min Act: -0.1699
Data Index: 609413 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2300. Min Range: -6.2300
Max Act: 6.0113. Min Act: -0.1700
Data Index: 8450086 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.9488. Min Act: -0.1700
Data Index: 7373269 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.9488. Min Act: -0.1700
Data Index: 8547691 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8863. Min Act: -0.1700
Data Index: 2290986 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8863. Min Act: -0.1700
Data Index: 1446671 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.8238. Min Act: -0.1700
Data Index: 7510775 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7925. Min Act: -0.1700
Data Index: 3179164 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7925. Min Act: -0.1700
Data Index: 671556 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7925. Min Act: -0.1700
Data Index: 3673726 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7925. Min Act: -0.1700
Data Index: 8628316 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7925. Min Act: -0.1700
Data Index: 3329244 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7613. Min Act: -0.1700
Data Index: 1447823 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7613. Min Act: -0.1700
Data Index: 8402638 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2300. Min Range: -6.2300
Max Act: 5.7613. Min Act: -0.1700
Data Index: 5505730 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19