Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3463. Min Range: -4.3463
Max Act: 4.3463. Min Act: -0.1700
Data Index: 3272993 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3463. Min Range: -4.3463
Max Act: 4.1276. Min Act: -0.1700
Data Index: 5335285 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.9088. Min Act: -0.1700
Data Index: 4371971 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.9088. Min Act: -0.1700
Data Index: 2130903 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.8462. Min Act: -0.1700
Data Index: 6306319 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.7837. Min Act: -0.1700
Data Index: 213143 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.7837. Min Act: -0.1700
Data Index: 3736267 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.7680. Min Act: -0.1700
Data Index: 5072830 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6742. Min Act: -0.1700
Data Index: 4911727 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6742. Min Act: -0.1700
Data Index: 4455038 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6742. Min Act: -0.1700
Data Index: 7198282 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6585. Min Act: -0.1700
Data Index: 5246190 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6742. Min Act: -0.1700
Data Index: 7179938 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6429. Min Act: -0.1700
Data Index: 8753203 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6272. Min Act: -0.1700
Data Index: 3334492 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6429. Min Act: -0.1700
Data Index: 3853957 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6272. Min Act: -0.1700
Data Index: 2439311 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.6272. Min Act: -0.1700
Data Index: 5237666 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.5959. Min Act: -0.1700
Data Index: 3973935 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3463. Min Range: -4.3463
Max Act: 3.5959. Min Act: -0.1700
Data Index: 8569506 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19