Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1287 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.4116. Min Act: -0.1700
Data Index: 6590781 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.3489. Min Act: -0.1700
Data Index: 6237231 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2704. Min Act: -0.1700
Data Index: 1065703 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.3018. Min Act: -0.1700
Data Index: 4269783 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.3018. Min Act: -0.1700
Data Index: 5202345 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.3018. Min Act: -0.1700
Data Index: 2081854 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2547. Min Act: -0.1700
Data Index: 5635834 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2389. Min Act: -0.1700
Data Index: 1369665 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2389. Min Act: -0.1700
Data Index: 7070718 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2389. Min Act: -0.1700
Data Index: 3336954 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2389. Min Act: -0.1700
Data Index: 6614322 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2232. Min Act: -0.1700
Data Index: 6036611 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2389. Min Act: -0.1700
Data Index: 1153013 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.1918. Min Act: -0.1700
Data Index: 357106 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2075. Min Act: -0.1700
Data Index: 3233041 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.1761. Min Act: -0.1700
Data Index: 3372815 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.2075. Min Act: -0.1700
Data Index: 3121845 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.1761. Min Act: -0.1700
Data Index: 7179698 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.1761. Min Act: -0.1700
Data Index: 785580 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4116. Min Range: -3.4116
Max Act: 3.1603. Min Act: -0.1700
Data Index: 4896965 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19