Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1676 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.6292. Min Act: -0.1700
Data Index: 1390498 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.5354. Min Act: -0.1700
Data Index: 3724354 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.5042. Min Act: -0.1700
Data Index: 5052912 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.4729. Min Act: -0.1700
Data Index: 1390497 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.4729. Min Act: -0.1700
Data Index: 6352534 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.4104. Min Act: -0.1700
Data Index: 986924 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.4104. Min Act: -0.1700
Data Index: 1763873 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3479. Min Act: -0.1700
Data Index: 6031955 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3166. Min Act: -0.1700
Data Index: 4461310 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3479. Min Act: -0.1700
Data Index: 3245369 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3166. Min Act: -0.1700
Data Index: 7503534 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.2854. Min Act: -0.1700
Data Index: 8499678 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3166. Min Act: -0.1700
Data Index: 8599618 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3166. Min Act: -0.1700
Data Index: 4594681 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3166. Min Act: -0.1700
Data Index: 6431504 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.2541. Min Act: -0.1700
Data Index: 5364954 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.3166. Min Act: -0.1700
Data Index: 4588072 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.2854. Min Act: -0.1700
Data Index: 5857385 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.2854. Min Act: -0.1700
Data Index: 4713830 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6292. Min Range: -4.6292
Max Act: 4.2854. Min Act: -0.1700
Data Index: 5886003 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19