Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4810 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.5797. Min Act: -0.1700
Data Index: 7943740 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.5172. Min Act: -0.1700
Data Index: 7716750 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.4860. Min Act: -0.1700
Data Index: 6452711 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.4235. Min Act: -0.1700
Data Index: 2845224 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.2672. Min Act: -0.1700
Data Index: 2154329 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.1422. Min Act: -0.1700
Data Index: 4724052 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.1110. Min Act: -0.1700
Data Index: 6425733 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.1110. Min Act: -0.1700
Data Index: 287756 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0797. Min Act: -0.1700
Data Index: 8334116 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0485. Min Act: -0.1700
Data Index: 2529651 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0485. Min Act: -0.1700
Data Index: 6471380 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0797. Min Act: -0.1700
Data Index: 957204 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0485. Min Act: -0.1700
Data Index: 6184618 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0485. Min Act: -0.1700
Data Index: 8311260 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0172. Min Act: -0.1700
Data Index: 1543659 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5797. Min Range: -7.5797
Max Act: 7.0172. Min Act: -0.1700
Data Index: 5818431 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5797. Min Range: -7.5797
Max Act: 6.9547. Min Act: -0.1700
Data Index: 8257321 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5797. Min Range: -7.5797
Max Act: 6.9547. Min Act: -0.1700
Data Index: 8391879 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5797. Min Range: -7.5797
Max Act: 6.9235. Min Act: -0.1700
Data Index: 1590023 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5797. Min Range: -7.5797
Max Act: 6.9235. Min Act: -0.1700
Data Index: 6140031 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19