Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2489 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.9216. Min Act: -0.1700
Data Index: 3394944 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.8591. Min Act: -0.1700
Data Index: 6463020 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.8591. Min Act: -0.1700
Data Index: 1575542 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.7341. Min Act: -0.1700
Data Index: 3408565 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.7966. Min Act: -0.1700
Data Index: 4393190 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.6091. Min Act: -0.1700
Data Index: 2656847 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.4841. Min Act: -0.1700
Data Index: 4449700 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.4841. Min Act: -0.1700
Data Index: 7366342 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.4216. Min Act: -0.1700
Data Index: 3052167 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.3591. Min Act: -0.1700
Data Index: 6532382 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.3591. Min Act: -0.1700
Data Index: 1508042 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.2966. Min Act: -0.1700
Data Index: 5886413 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.2966. Min Act: -0.1700
Data Index: 3044583 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.3591. Min Act: -0.1700
Data Index: 2815715 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.2341. Min Act: -0.1700
Data Index: 1149400 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.2341. Min Act: -0.1700
Data Index: 6284169 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.1716. Min Act: -0.1700
Data Index: 3610960 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.2341. Min Act: -0.1700
Data Index: 7168801 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.1091. Min Act: -0.1700
Data Index: 6363160 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9216. Min Range: -8.9216
Max Act: 8.1091. Min Act: -0.1700
Data Index: 2605587 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19