Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2094 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4790. Min Range: -7.4790
Max Act: 7.4790. Min Act: -0.1700
Data Index: 4533025 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4790. Min Range: -7.4790
Max Act: 7.2915. Min Act: -0.1700
Data Index: 3275625 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4790. Min Range: -7.4790
Max Act: 7.1352. Min Act: -0.1700
Data Index: 6091616 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4790. Min Range: -7.4790
Max Act: 7.0727. Min Act: -0.1700
Data Index: 3730472 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4790. Min Range: -7.4790
Max Act: 7.0415. Min Act: -0.1700
Data Index: 8505644 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.9477. Min Act: -0.1700
Data Index: 1674122 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.9477. Min Act: -0.1700
Data Index: 7420848 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.9165. Min Act: -0.1700
Data Index: 1407071 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.8852. Min Act: -0.1700
Data Index: 2541649 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.8852. Min Act: -0.1700
Data Index: 6926291 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.8227. Min Act: -0.1700
Data Index: 7090163 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.8227. Min Act: -0.1700
Data Index: 8460934 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.8540. Min Act: -0.1700
Data Index: 5683016 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.8227. Min Act: -0.1700
Data Index: 8428417 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.7915. Min Act: -0.1700
Data Index: 6455616 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.7602. Min Act: -0.1700
Data Index: 5469737 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.7915. Min Act: -0.1700
Data Index: 7302027 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.7602. Min Act: -0.1700
Data Index: 1396461 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.7602. Min Act: -0.1700
Data Index: 1325198 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4790. Min Range: -7.4790
Max Act: 6.7602. Min Act: -0.1700
Data Index: 7210294 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19