Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1753 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.7820. Min Act: -0.1700
Data Index: 7259381 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.5632. Min Act: -0.1700
Data Index: 3700719 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.4695. Min Act: -0.1700
Data Index: 4408389 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.3757. Min Act: -0.1700
Data Index: 2882757 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.3757. Min Act: -0.1700
Data Index: 8737153 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.3757. Min Act: -0.1700
Data Index: 4215669 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.3132. Min Act: -0.1700
Data Index: 5958676 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.2820. Min Act: -0.1700
Data Index: 1582143 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.2820. Min Act: -0.1700
Data Index: 5585854 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.2507. Min Act: -0.1700
Data Index: 2387955 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1882. Min Act: -0.1700
Data Index: 2394100 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1882. Min Act: -0.1700
Data Index: 4993324 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1570. Min Act: -0.1700
Data Index: 7940624 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1570. Min Act: -0.1700
Data Index: 7137707 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1570. Min Act: -0.1700
Data Index: 6933915 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1570. Min Act: -0.1700
Data Index: 6348319 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1882. Min Act: -0.1700
Data Index: 7392839 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1257. Min Act: -0.1700
Data Index: 4533158 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.1257. Min Act: -0.1700
Data Index: 1361381 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7820. Min Range: -6.7820
Max Act: 6.0945. Min Act: -0.1700
Data Index: 5618973 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19