Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.6601. Min Act: -0.1700
Data Index: 4380055 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.5976. Min Act: -0.1700
Data Index: 7833153 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.5039. Min Act: -0.1700
Data Index: 5694478 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.4726. Min Act: -0.1700
Data Index: 1260 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.4101. Min Act: -0.1700
Data Index: 4411808 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.4414. Min Act: -0.1700
Data Index: 2393460 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.4414. Min Act: -0.1700
Data Index: 1254698 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.3789. Min Act: -0.1700
Data Index: 1928996 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.3789. Min Act: -0.1700
Data Index: 910679 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.3164. Min Act: -0.1700
Data Index: 158771 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.3164. Min Act: -0.1700
Data Index: 5285408 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.3164. Min Act: -0.1700
Data Index: 2627181 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.2851. Min Act: -0.1700
Data Index: 8098701 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.3164. Min Act: -0.1700
Data Index: 4226076 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.2851. Min Act: -0.1700
Data Index: 2382353 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.2851. Min Act: -0.1700
Data Index: 2549612 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.3164. Min Act: -0.1700
Data Index: 7381840 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.2539. Min Act: -0.1700
Data Index: 4291187 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.1914. Min Act: -0.1700
Data Index: 6062781 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6601. Min Range: -5.6601
Max Act: 5.2226. Min Act: -0.1700
Data Index: 8513924 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19