Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1086 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.8058. Min Act: -0.1700
Data Index: 4504153 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.8058. Min Act: -0.1700
Data Index: 1405397 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.7120. Min Act: -0.1700
Data Index: 8364528 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.7120. Min Act: -0.1700
Data Index: 2447503 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.6494. Min Act: -0.1700
Data Index: 6451873 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.6807. Min Act: -0.1700
Data Index: 5015998 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.5712. Min Act: -0.1700
Data Index: 8442736 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.5712. Min Act: -0.1700
Data Index: 5387036 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.5399. Min Act: -0.1700
Data Index: 7876762 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.5399. Min Act: -0.1700
Data Index: 3058755 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.5242. Min Act: -0.1700
Data Index: 4559707 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.5399. Min Act: -0.1700
Data Index: 6008562 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.5085. Min Act: -0.1700
Data Index: 8435270 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.4929. Min Act: -0.1700
Data Index: 5264598 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.4929. Min Act: -0.1700
Data Index: 7591596 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.4929. Min Act: -0.1700
Data Index: 8618998 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.4929. Min Act: -0.1700
Data Index: 3899684 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.4772. Min Act: -0.1700
Data Index: 392068 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.4615. Min Act: -0.1700
Data Index: 5493695 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8058. Min Range: -3.8058
Max Act: 3.4459. Min Act: -0.1700
Data Index: 2291550 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19