Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3245 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2205. Min Range: -5.2205
Max Act: 5.2205. Min Act: -0.1700
Data Index: 2150640 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9393. Min Act: -0.1700
Data Index: 950549 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.9080. Min Act: -0.1700
Data Index: 315015 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8768. Min Act: -0.1700
Data Index: 4395579 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 8376032 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 7733773 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8455. Min Act: -0.1700
Data Index: 7821796 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8143. Min Act: -0.1700
Data Index: 288153 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8143. Min Act: -0.1700
Data Index: 288152 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8143. Min Act: -0.1700
Data Index: 947796 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8143. Min Act: -0.1700
Data Index: 5871193 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8143. Min Act: -0.1700
Data Index: 7733781 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.8143. Min Act: -0.1700
Data Index: 1061720 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.7830. Min Act: -0.1700
Data Index: 7713907 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.7830. Min Act: -0.1700
Data Index: 3567882 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.7830. Min Act: -0.1700
Data Index: 4395578 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.7830. Min Act: -0.1700
Data Index: 6878443 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.7518. Min Act: -0.1700
Data Index: 2569427 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.7518. Min Act: -0.1700
Data Index: 3620038 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2205. Min Range: -5.2205
Max Act: 4.7518. Min Act: -0.1700
Data Index: 2239469 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19