Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3007 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.3460. Min Act: -0.1700
Data Index: 5754107 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.2835. Min Act: -0.1700
Data Index: 8416600 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1897. Min Act: -0.1700
Data Index: 7808860 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.2210. Min Act: -0.1700
Data Index: 8243390 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1585. Min Act: -0.1700
Data Index: 7813350 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1585. Min Act: -0.1700
Data Index: 5319228 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1585. Min Act: -0.1700
Data Index: 3142801 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1272. Min Act: -0.1700
Data Index: 4222381 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1272. Min Act: -0.1700
Data Index: 3181629 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.1272. Min Act: -0.1700
Data Index: 5316063 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0960. Min Act: -0.1700
Data Index: 869391 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0647. Min Act: -0.1700
Data Index: 3480063 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0647. Min Act: -0.1700
Data Index: 6358981 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0647. Min Act: -0.1700
Data Index: 5680805 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0334. Min Act: -0.1700
Data Index: 3586599 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0647. Min Act: -0.1700
Data Index: 8070925 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0334. Min Act: -0.1700
Data Index: 5754104 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0334. Min Act: -0.1700
Data Index: 5083472 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3460. Min Range: -4.3460
Max Act: 4.0022. Min Act: -0.1700
Data Index: 7720877 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3460. Min Range: -4.3460
Max Act: 3.9709. Min Act: -0.1700
Data Index: 7044332 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19