Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4559 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1234. Min Range: -3.1234
Max Act: 3.1234. Min Act: -0.1700
Data Index: 348826 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1234. Min Range: -3.1234
Max Act: 3.1077. Min Act: -0.1700
Data Index: 1103080 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1234. Min Range: -3.1234
Max Act: 3.0762. Min Act: -0.1700
Data Index: 1578706 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1234. Min Range: -3.1234
Max Act: 3.0288. Min Act: -0.1700
Data Index: 1586005 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1234. Min Range: -3.1234
Max Act: 3.0130. Min Act: -0.1700
Data Index: 4076570 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9972. Min Act: -0.1700
Data Index: 8771870 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9972. Min Act: -0.1700
Data Index: 8507606 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9814. Min Act: -0.1700
Data Index: 5555774 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9339. Min Act: -0.1700
Data Index: 4108608 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9181. Min Act: -0.1700
Data Index: 7630831 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9022. Min Act: -0.1700
Data Index: 3523878 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9022. Min Act: -0.1700
Data Index: 6579738 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9022. Min Act: -0.1700
Data Index: 3679311 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9022. Min Act: -0.1700
Data Index: 947289 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.8864. Min Act: -0.1700
Data Index: 6559972 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.9022. Min Act: -0.1700
Data Index: 5734352 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.8864. Min Act: -0.1700
Data Index: 3501384 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.8864. Min Act: -0.1700
Data Index: 8351235 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.8705. Min Act: -0.1700
Data Index: 5381441 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1234. Min Range: -3.1234
Max Act: 2.8705. Min Act: -0.1700
Data Index: 616026 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19