Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2386. Min Range: -7.2386
Max Act: 7.2386. Min Act: -0.1700
Data Index: 6129927 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2386. Min Range: -7.2386
Max Act: 7.2386. Min Act: -0.1700
Data Index: 4434295 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.9886. Min Act: -0.1700
Data Index: 2135133 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.9261. Min Act: -0.1700
Data Index: 5201405 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.8636. Min Act: -0.1700
Data Index: 6389292 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.8636. Min Act: -0.1700
Data Index: 6270257 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.8323. Min Act: -0.1700
Data Index: 6823776 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.8323. Min Act: -0.1700
Data Index: 1130648 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.7698. Min Act: -0.1700
Data Index: 3339137 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.7386. Min Act: -0.1700
Data Index: 4567313 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.7386. Min Act: -0.1700
Data Index: 5228523 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.7386. Min Act: -0.1700
Data Index: 5137634 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.7073. Min Act: -0.1700
Data Index: 6544792 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.6761. Min Act: -0.1700
Data Index: 7774548 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.6761. Min Act: -0.1700
Data Index: 867333 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.6448. Min Act: -0.1700
Data Index: 7416545 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.6448. Min Act: -0.1700
Data Index: 7202372 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.6136. Min Act: -0.1700
Data Index: 657385 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.6448. Min Act: -0.1700
Data Index: 841993 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2386. Min Range: -7.2386
Max Act: 6.6136. Min Act: -0.1700
Data Index: 3514177 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19