Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.5842. Min Act: -0.1700
Data Index: 7920967 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.5216. Min Act: -0.1700
Data Index: 6396393 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.5216. Min Act: -0.1700
Data Index: 8469169 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4903. Min Act: -0.1700
Data Index: 2267040 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4590. Min Act: -0.1700
Data Index: 714929 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4590. Min Act: -0.1700
Data Index: 4982233 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4433. Min Act: -0.1700
Data Index: 7216019 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4276. Min Act: -0.1700
Data Index: 7077190 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4276. Min Act: -0.1700
Data Index: 4667333 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4276. Min Act: -0.1700
Data Index: 3952881 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.3963. Min Act: -0.1700
Data Index: 2956416 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4119. Min Act: -0.1700
Data Index: 1453151 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.3963. Min Act: -0.1700
Data Index: 4796925 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.3806. Min Act: -0.1700
Data Index: 2516524 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4119. Min Act: -0.1700
Data Index: 6438828 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.4276. Min Act: -0.1700
Data Index: 2632643 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.3963. Min Act: -0.1700
Data Index: 2054064 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.3806. Min Act: -0.1700
Data Index: 6434340 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.3963. Min Act: -0.1700
Data Index: 6092357 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5842. Min Range: -3.5842
Max Act: 3.3963. Min Act: -0.1700
Data Index: 6116113 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19