Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 332 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1529. Min Range: -7.1529
Max Act: 7.1529. Min Act: -0.1700
Data Index: 8272223 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1529. Min Range: -7.1529
Max Act: 7.0279. Min Act: -0.1700
Data Index: 3337267 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.9654. Min Act: -0.1700
Data Index: 568532 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.9654. Min Act: -0.1700
Data Index: 5818343 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.9029. Min Act: -0.1700
Data Index: 662543 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.8404. Min Act: -0.1700
Data Index: 5479295 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.8404. Min Act: -0.1700
Data Index: 4835306 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.8404. Min Act: -0.1700
Data Index: 1951168 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.8091. Min Act: -0.1700
Data Index: 5324945 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.7466. Min Act: -0.1700
Data Index: 1379747 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.7779. Min Act: -0.1700
Data Index: 3030244 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.7779. Min Act: -0.1700
Data Index: 6208098 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.7466. Min Act: -0.1700
Data Index: 6811900 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.7466. Min Act: -0.1700
Data Index: 1111805 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.7154. Min Act: -0.1700
Data Index: 100881 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.6841. Min Act: -0.1700
Data Index: 949714 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.6841. Min Act: -0.1700
Data Index: 4988132 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.6841. Min Act: -0.1700
Data Index: 6129091 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.6529. Min Act: -0.1700
Data Index: 5865443 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1529. Min Range: -7.1529
Max Act: 6.6529. Min Act: -0.1700
Data Index: 7926486 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19