Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1711 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9956. Min Act: -0.1700
Data Index: 4866179 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9644. Min Act: -0.1700
Data Index: 1674922 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.9331. Min Act: -0.1700
Data Index: 7022391 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8706. Min Act: -0.1700
Data Index: 6759113 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8706. Min Act: -0.1700
Data Index: 4755197 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8706. Min Act: -0.1700
Data Index: 8491536 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8706. Min Act: -0.1700
Data Index: 2506709 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 4011703 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 6319997 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 5282528 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 5149377 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 8716984 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 2442048 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 8588424 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8393. Min Act: -0.1700
Data Index: 7410521 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 1868827 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 2515092 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 3040281 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 5878002 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9956. Min Range: -3.9956
Max Act: 3.8080. Min Act: -0.1700
Data Index: 5972160 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19