Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.8326. Min Act: -0.1700
Data Index: 978113 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.8326. Min Act: -0.1700
Data Index: 2693952 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.8014. Min Act: -0.1700
Data Index: 7728226 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.8014. Min Act: -0.1700
Data Index: 6558634 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7389. Min Act: -0.1700
Data Index: 7679384 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7389. Min Act: -0.1700
Data Index: 2324018 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7389. Min Act: -0.1700
Data Index: 3623566 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7076. Min Act: -0.1700
Data Index: 2775673 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7076. Min Act: -0.1700
Data Index: 2084977 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7076. Min Act: -0.1700
Data Index: 6170447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7076. Min Act: -0.1700
Data Index: 3375036 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.6764. Min Act: -0.1700
Data Index: 7610806 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7076. Min Act: -0.1700
Data Index: 7940812 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.6764. Min Act: -0.1700
Data Index: 1196326 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.6764. Min Act: -0.1700
Data Index: 6264022 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.7076. Min Act: -0.1700
Data Index: 72112 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.6764. Min Act: -0.1700
Data Index: 6368854 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.6764. Min Act: -0.1700
Data Index: 5805870 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.6764. Min Act: -0.1700
Data Index: 4144521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8326. Min Range: -5.8326
Max Act: 5.6764. Min Act: -0.1700
Data Index: 7578405 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19