Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.2960. Min Act: -0.1700
Data Index: 8299444 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.2335. Min Act: -0.1700
Data Index: 8562032 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.1397. Min Act: -0.1700
Data Index: 5353568 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.1397. Min Act: -0.1700
Data Index: 7961760 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.1085. Min Act: -0.1700
Data Index: 1941321 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.1085. Min Act: -0.1700
Data Index: 1693034 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0772. Min Act: -0.1700
Data Index: 6909673 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0772. Min Act: -0.1700
Data Index: 191501 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0772. Min Act: -0.1700
Data Index: 8631795 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0772. Min Act: -0.1700
Data Index: 5273390 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0460. Min Act: -0.1700
Data Index: 5631723 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0460. Min Act: -0.1700
Data Index: 3044409 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0147. Min Act: -0.1700
Data Index: 1659233 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0460. Min Act: -0.1700
Data Index: 8202219 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0460. Min Act: -0.1700
Data Index: 1747563 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0460. Min Act: -0.1700
Data Index: 3032147 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0460. Min Act: -0.1700
Data Index: 1749781 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0460. Min Act: -0.1700
Data Index: 107368 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0147. Min Act: -0.1700
Data Index: 1253886 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2960. Min Range: -5.2960
Max Act: 5.0147. Min Act: -0.1700
Data Index: 100929 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19