Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.9405. Min Act: -0.1700
Data Index: 957949 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8894. Min Act: -0.1700
Data Index: 6598929 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8552. Min Act: -0.1700
Data Index: 5084031 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8552. Min Act: -0.1700
Data Index: 6802473 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8552. Min Act: -0.1700
Data Index: 6268232 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8209. Min Act: -0.1700
Data Index: 4000252 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8381. Min Act: -0.1700
Data Index: 2389323 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8209. Min Act: -0.1700
Data Index: 7181523 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8038. Min Act: -0.1700
Data Index: 6463397 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8209. Min Act: -0.1700
Data Index: 8317438 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7693. Min Act: -0.1700
Data Index: 7520996 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7693. Min Act: -0.1700
Data Index: 2901952 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7865. Min Act: -0.1700
Data Index: 4853044 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7865. Min Act: -0.1700
Data Index: 1078887 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7865. Min Act: -0.1700
Data Index: 7647296 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.8038. Min Act: -0.1700
Data Index: 3080165 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7865. Min Act: -0.1700
Data Index: 2514806 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7865. Min Act: -0.1700
Data Index: 3836918 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7693. Min Act: -0.1700
Data Index: 4964239 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9405. Min Range: -1.9405
Max Act: 1.7520. Min Act: -0.1700
Data Index: 2403168 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19