Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 713 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1980. Min Act: -0.1700
Data Index: 5792584 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1814. Min Act: -0.1700
Data Index: 5194556 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1980. Min Act: -0.1700
Data Index: 6769973 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1814. Min Act: -0.1700
Data Index: 6769974 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1980. Min Act: -0.1700
Data Index: 8245697 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1814. Min Act: -0.1700
Data Index: 3214861 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1481. Min Act: -0.1700
Data Index: 2002428 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1647. Min Act: -0.1700
Data Index: 6039261 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1481. Min Act: -0.1700
Data Index: 5982110 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1481. Min Act: -0.1700
Data Index: 6007876 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1481. Min Act: -0.1700
Data Index: 4893689 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1314. Min Act: -0.1700
Data Index: 4175630 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1314. Min Act: -0.1700
Data Index: 2113521 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1147. Min Act: -0.1700
Data Index: 6182891 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1147. Min Act: -0.1700
Data Index: 1571422 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.1314. Min Act: -0.1700
Data Index: 203394 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.0980. Min Act: -0.1700
Data Index: 5396730 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.0980. Min Act: -0.1700
Data Index: 6317391 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.0980. Min Act: -0.1700
Data Index: 5968983 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1980. Min Range: -2.1980
Max Act: 2.0980. Min Act: -0.1700
Data Index: 3499131 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19