Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2895 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1489. Min Range: -4.1489
Max Act: 4.1489. Min Act: -0.1700
Data Index: 6418814 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.9926. Min Act: -0.1700
Data Index: 7104061 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.9300. Min Act: -0.1700
Data Index: 43163 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8675. Min Act: -0.1700
Data Index: 92396 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8675. Min Act: -0.1700
Data Index: 8056362 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8362. Min Act: -0.1700
Data Index: 6630852 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8362. Min Act: -0.1700
Data Index: 8071019 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8050. Min Act: -0.1700
Data Index: 3333146 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8050. Min Act: -0.1700
Data Index: 5291301 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8050. Min Act: -0.1700
Data Index: 488095 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7737. Min Act: -0.1700
Data Index: 8421891 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7737. Min Act: -0.1700
Data Index: 2400682 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.8050. Min Act: -0.1700
Data Index: 4587945 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7737. Min Act: -0.1700
Data Index: 6718483 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7737. Min Act: -0.1700
Data Index: 1469714 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7424. Min Act: -0.1700
Data Index: 4399652 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7737. Min Act: -0.1700
Data Index: 267392 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7737. Min Act: -0.1700
Data Index: 1274831 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7737. Min Act: -0.1700
Data Index: 3447446 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1489. Min Range: -4.1489
Max Act: 3.7424. Min Act: -0.1700
Data Index: 681746 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19