Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3617 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0553. Min Range: -6.0553
Max Act: 6.0553. Min Act: -0.1700
Data Index: 487827 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.8053. Min Act: -0.1700
Data Index: 475458 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.6490. Min Act: -0.1700
Data Index: 1997485 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.6490. Min Act: -0.1700
Data Index: 757027 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5553. Min Act: -0.1700
Data Index: 958188 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5240. Min Act: -0.1700
Data Index: 2854930 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.5240. Min Act: -0.1700
Data Index: 2592619 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4615. Min Act: -0.1700
Data Index: 6921167 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4303. Min Act: -0.1700
Data Index: 1088813 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.4303. Min Act: -0.1700
Data Index: 5558525 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3990. Min Act: -0.1700
Data Index: 2876172 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3990. Min Act: -0.1700
Data Index: 899948 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3365. Min Act: -0.1700
Data Index: 6670758 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3678. Min Act: -0.1700
Data Index: 8017045 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3365. Min Act: -0.1700
Data Index: 611834 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3365. Min Act: -0.1700
Data Index: 7801301 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.2740. Min Act: -0.1700
Data Index: 757026 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3053. Min Act: -0.1700
Data Index: 2592613 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.2740. Min Act: -0.1700
Data Index: 2592618 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0553. Min Range: -6.0553
Max Act: 5.3053. Min Act: -0.1700
Data Index: 7284412 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19