Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 257 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3290. Min Range: -4.3290
Max Act: 4.3290. Min Act: -0.1700
Data Index: 7408055 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3290. Min Range: -4.3290
Max Act: 4.1102. Min Act: -0.1700
Data Index: 3612066 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3290. Min Range: -4.3290
Max Act: 4.0477. Min Act: -0.1700
Data Index: 8490355 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3290. Min Range: -4.3290
Max Act: 4.0165. Min Act: -0.1700
Data Index: 1109301 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.9852. Min Act: -0.1700
Data Index: 2694552 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.9852. Min Act: -0.1700
Data Index: 5764333 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.9539. Min Act: -0.1700
Data Index: 7711676 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.9227. Min Act: -0.1700
Data Index: 3791147 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.9227. Min Act: -0.1700
Data Index: 7937174 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8914. Min Act: -0.1700
Data Index: 3463945 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8914. Min Act: -0.1700
Data Index: 8223105 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8914. Min Act: -0.1700
Data Index: 7807479 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8914. Min Act: -0.1700
Data Index: 6368379 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8914. Min Act: -0.1700
Data Index: 1571948 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8914. Min Act: -0.1700
Data Index: 3895935 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8601. Min Act: -0.1700
Data Index: 5944352 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8601. Min Act: -0.1700
Data Index: 7552708 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8601. Min Act: -0.1700
Data Index: 7503010 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8601. Min Act: -0.1700
Data Index: 4110064 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3290. Min Range: -4.3290
Max Act: 3.8601. Min Act: -0.1700
Data Index: 5281321 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19