Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.9568. Min Act: -0.1700
Data Index: 8681414 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.9568. Min Act: -0.1700
Data Index: 5654637 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.9568. Min Act: -0.1700
Data Index: 958587 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8943. Min Act: -0.1700
Data Index: 547430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8630. Min Act: -0.1700
Data Index: 2999898 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8630. Min Act: -0.1700
Data Index: 932380 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8318. Min Act: -0.1700
Data Index: 5244000 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8318. Min Act: -0.1700
Data Index: 8790685 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8318. Min Act: -0.1700
Data Index: 416833 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8318. Min Act: -0.1700
Data Index: 819092 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8005. Min Act: -0.1700
Data Index: 7677534 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8005. Min Act: -0.1700
Data Index: 2631699 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.8318. Min Act: -0.1700
Data Index: 6067388 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.7693. Min Act: -0.1700
Data Index: 3678040 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.7693. Min Act: -0.1700
Data Index: 4501640 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.7693. Min Act: -0.1700
Data Index: 3028656 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.7380. Min Act: -0.1700
Data Index: 4416576 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.7068. Min Act: -0.1700
Data Index: 2182223 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.7380. Min Act: -0.1700
Data Index: 6007944 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9568. Min Range: -4.9568
Max Act: 4.7068. Min Act: -0.1700
Data Index: 3871950 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19