Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1359 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.6088. Min Act: -0.1700
Data Index: 951784 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.5776. Min Act: -0.1700
Data Index: 1724279 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.4838. Min Act: -0.1700
Data Index: 5395269 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.3588. Min Act: -0.1700
Data Index: 8743230 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6128163 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.3588. Min Act: -0.1700
Data Index: 7461143 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6150563 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6375967 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.3276. Min Act: -0.1700
Data Index: 7429756 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.2963. Min Act: -0.1700
Data Index: 3419394 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.3276. Min Act: -0.1700
Data Index: 6141260 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.2963. Min Act: -0.1700
Data Index: 2075377 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.2963. Min Act: -0.1700
Data Index: 8735703 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.2651. Min Act: -0.1700
Data Index: 5415454 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.2651. Min Act: -0.1700
Data Index: 7856822 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.2026. Min Act: -0.1700
Data Index: 663623 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.2026. Min Act: -0.1700
Data Index: 5797704 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.1713. Min Act: -0.1700
Data Index: 6081747 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.1401. Min Act: -0.1700
Data Index: 4843138 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6088. Min Range: -5.6088
Max Act: 5.1713. Min Act: -0.1700
Data Index: 6415144 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19