Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1544 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.8190. Min Act: -0.1700
Data Index: 3761788 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.7878. Min Act: -0.1700
Data Index: 5687977 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.7565. Min Act: -0.1700
Data Index: 3296741 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.7252. Min Act: -0.1700
Data Index: 3834982 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6783. Min Act: -0.1700
Data Index: 7478272 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.7096. Min Act: -0.1700
Data Index: 8530439 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6783. Min Act: -0.1700
Data Index: 3071028 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6783. Min Act: -0.1700
Data Index: 6447658 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6783. Min Act: -0.1700
Data Index: 6392712 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6470. Min Act: -0.1700
Data Index: 6382135 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6157. Min Act: -0.1700
Data Index: 5142792 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6313. Min Act: -0.1700
Data Index: 3340683 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6157. Min Act: -0.1700
Data Index: 8340616 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5844. Min Act: -0.1700
Data Index: 962774 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.6000. Min Act: -0.1700
Data Index: 4625716 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5844. Min Act: -0.1700
Data Index: 3954393 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5687. Min Act: -0.1700
Data Index: 5804179 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5531. Min Act: -0.1700
Data Index: 8580342 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5374. Min Act: -0.1700
Data Index: 7189480 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8190. Min Range: -3.8190
Max Act: 3.5218. Min Act: -0.1700
Data Index: 2692411 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19