Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1692 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.6576. Min Act: -0.1700
Data Index: 6590803 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.5014. Min Act: -0.1700
Data Index: 7626471 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.4701. Min Act: -0.1700
Data Index: 6061028 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.4076. Min Act: -0.1700
Data Index: 6279038 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.3764. Min Act: -0.1700
Data Index: 4388883 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.3451. Min Act: -0.1700
Data Index: 6224359 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.3451. Min Act: -0.1700
Data Index: 7979581 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.3451. Min Act: -0.1700
Data Index: 637045 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2514. Min Act: -0.1700
Data Index: 3226992 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2514. Min Act: -0.1700
Data Index: 2947589 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2514. Min Act: -0.1700
Data Index: 2885691 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2826. Min Act: -0.1700
Data Index: 8519432 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.3139. Min Act: -0.1700
Data Index: 8511194 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2201. Min Act: -0.1700
Data Index: 389897 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2514. Min Act: -0.1700
Data Index: 1834794 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2201. Min Act: -0.1700
Data Index: 8519436 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.1889. Min Act: -0.1700
Data Index: 5050284 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2201. Min Act: -0.1700
Data Index: 1686560 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2514. Min Act: -0.1700
Data Index: 2341218 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6576. Min Range: -5.6576
Max Act: 5.2201. Min Act: -0.1700
Data Index: 7848195 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19