Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4858. Min Range: -7.4858
Max Act: 7.4858. Min Act: -0.1700
Data Index: 4727764 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4858. Min Range: -7.4858
Max Act: 7.3295. Min Act: -0.1700
Data Index: 3650534 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4858. Min Range: -7.4858
Max Act: 7.1733. Min Act: -0.1700
Data Index: 1584304 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4858. Min Range: -7.4858
Max Act: 7.0795. Min Act: -0.1700
Data Index: 2241198 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4858. Min Range: -7.4858
Max Act: 7.0170. Min Act: -0.1700
Data Index: 5579980 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.9545. Min Act: -0.1700
Data Index: 783670 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.8920. Min Act: -0.1700
Data Index: 1833541 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.8920. Min Act: -0.1700
Data Index: 6000514 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.8920. Min Act: -0.1700
Data Index: 8372967 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.8920. Min Act: -0.1700
Data Index: 1930260 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.8608. Min Act: -0.1700
Data Index: 7119503 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.8608. Min Act: -0.1700
Data Index: 32314 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.8608. Min Act: -0.1700
Data Index: 5732857 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.7983. Min Act: -0.1700
Data Index: 120769 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.7983. Min Act: -0.1700
Data Index: 164483 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.7670. Min Act: -0.1700
Data Index: 496960 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.7670. Min Act: -0.1700
Data Index: 1892882 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.7358. Min Act: -0.1700
Data Index: 1529363 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.7358. Min Act: -0.1700
Data Index: 6711475 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4858. Min Range: -7.4858
Max Act: 6.7358. Min Act: -0.1700
Data Index: 4682512 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19