Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 74 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.9960. Min Act: -0.1700
Data Index: 8225469 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.9960. Min Act: -0.1700
Data Index: 6189538 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.9648. Min Act: -0.1700
Data Index: 3333449 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.9335. Min Act: -0.1700
Data Index: 4864340 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.9022. Min Act: -0.1700
Data Index: 2756762 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8710. Min Act: -0.1700
Data Index: 8795566 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8710. Min Act: -0.1700
Data Index: 4890650 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8710. Min Act: -0.1700
Data Index: 4583932 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8710. Min Act: -0.1700
Data Index: 7487528 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8397. Min Act: -0.1700
Data Index: 2837989 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8553. Min Act: -0.1700
Data Index: 487712 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8553. Min Act: -0.1700
Data Index: 6041367 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8710. Min Act: -0.1700
Data Index: 3419933 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8241. Min Act: -0.1700
Data Index: 5256159 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8397. Min Act: -0.1700
Data Index: 7572157 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8241. Min Act: -0.1700
Data Index: 4003760 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8397. Min Act: -0.1700
Data Index: 3409868 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8241. Min Act: -0.1700
Data Index: 8310627 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.8241. Min Act: -0.1700
Data Index: 5009105 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9960. Min Range: -3.9960
Max Act: 3.7928. Min Act: -0.1700
Data Index: 4845641 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19