Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1988. Min Act: -0.1700
Data Index: 1191034 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1988. Min Act: -0.1700
Data Index: 8808533 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1675. Min Act: -0.1700
Data Index: 8752455 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1363. Min Act: -0.1700
Data Index: 2959613 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1363. Min Act: -0.1700
Data Index: 7215223 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1700
Data Index: 2906923 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1700
Data Index: 5139916 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1697
Data Index: 1807436 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1700
Data Index: 2906919 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.0738. Min Act: -0.1691
Data Index: 582025 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1696
Data Index: 4906063 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1696
Data Index: 7951274 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1700
Data Index: 92350 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1698
Data Index: 6734483 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.0738. Min Act: -0.1700
Data Index: 376662 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1700
Data Index: 6734487 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.0738. Min Act: -0.1700
Data Index: 3857179 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1050. Min Act: -0.1700
Data Index: 3246030 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.1363. Min Act: -0.1667
Data Index: 6533603 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1988. Min Range: -6.1988
Max Act: 6.0425. Min Act: -0.1684
Data Index: 4967596 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19