Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.2031. Min Act: -0.1700
Data Index: 462341 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1406. Min Act: -0.1700
Data Index: 203172 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1093. Min Act: -0.1700
Data Index: 5494892 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.1093. Min Act: -0.1700
Data Index: 7263124 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2031. Min Range: -6.2031
Max Act: 6.0156. Min Act: -0.1700
Data Index: 7037906 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9843. Min Act: -0.1700
Data Index: 4640106 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9843. Min Act: -0.1700
Data Index: 8002370 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 3188941 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6111232 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8906. Min Act: -0.1700
Data Index: 3491377 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8593. Min Act: -0.1700
Data Index: 1032979 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8593. Min Act: -0.1700
Data Index: 4443455 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8593. Min Act: -0.1700
Data Index: 3795679 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8593. Min Act: -0.1700
Data Index: 7627578 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.8593. Min Act: -0.1700
Data Index: 8657680 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7968. Min Act: -0.1700
Data Index: 7120224 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7968. Min Act: -0.1700
Data Index: 4599383 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7968. Min Act: -0.1700
Data Index: 8346386 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7656. Min Act: -0.1700
Data Index: 4433034 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2031. Min Range: -6.2031
Max Act: 5.7968. Min Act: -0.1700
Data Index: 2783051 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19