Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 146 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.3186. Min Act: -0.1700
Data Index: 6158522 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.3186. Min Act: -0.1700
Data Index: 8619378 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.2874. Min Act: -0.1700
Data Index: 108805 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.3186. Min Act: -0.1700
Data Index: 8245924 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.2874. Min Act: -0.1700
Data Index: 5848316 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.2561. Min Act: -0.1700
Data Index: 5848314 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.2249. Min Act: -0.1700
Data Index: 4525538 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1936. Min Act: -0.1700
Data Index: 8668438 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1936. Min Act: -0.1700
Data Index: 2133027 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1936. Min Act: -0.1700
Data Index: 8169168 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1936. Min Act: -0.1700
Data Index: 544456 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1624. Min Act: -0.1700
Data Index: 7053590 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1624. Min Act: -0.1700
Data Index: 4432775 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1624. Min Act: -0.1700
Data Index: 2027811 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1624. Min Act: -0.1700
Data Index: 8392108 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1624. Min Act: -0.1700
Data Index: 7385153 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1624. Min Act: -0.1700
Data Index: 754695 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1311. Min Act: -0.1700
Data Index: 6842453 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1311. Min Act: -0.1700
Data Index: 8383892 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3186. Min Range: -5.3186
Max Act: 5.1311. Min Act: -0.1700
Data Index: 4476602 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19