Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4930 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.5654. Min Act: -0.1700
Data Index: 6119445 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.5654. Min Act: -0.1700
Data Index: 2914832 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.4715. Min Act: -0.1700
Data Index: 8251056 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3461. Min Act: -0.1700
Data Index: 7315305 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3461. Min Act: -0.1700
Data Index: 760684 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3147. Min Act: -0.1700
Data Index: 7600379 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3147. Min Act: -0.1700
Data Index: 6242169 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3147. Min Act: -0.1700
Data Index: 5653465 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3147. Min Act: -0.1700
Data Index: 7012110 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3147. Min Act: -0.1700
Data Index: 602629 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.3147. Min Act: -0.1700
Data Index: 4680094 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2833. Min Act: -0.1700
Data Index: 5244247 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2833. Min Act: -0.1700
Data Index: 2542274 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2833. Min Act: -0.1700
Data Index: 3248202 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2833. Min Act: -0.1700
Data Index: 1523913 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2833. Min Act: -0.1700
Data Index: 6921554 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2519. Min Act: -0.1700
Data Index: 3488615 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2833. Min Act: -0.1700
Data Index: 5875032 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2519. Min Act: -0.1700
Data Index: 6751243 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5654. Min Range: -3.5654
Max Act: 3.2361. Min Act: -0.1700
Data Index: 2545666 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19