Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0239. Min Range: -8.0239
Max Act: 8.0239. Min Act: -0.1700
Data Index: 7910985 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.9614. Min Act: -0.1700
Data Index: 6254096 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.8989. Min Act: -0.1700
Data Index: 5859156 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.8989. Min Act: -0.1700
Data Index: 7210804 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.8989. Min Act: -0.1700
Data Index: 1532911 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.8989. Min Act: -0.1700
Data Index: 5829374 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.8364. Min Act: -0.1700
Data Index: 941240 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.8364. Min Act: -0.1700
Data Index: 6335861 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.8364. Min Act: -0.1700
Data Index: 5260073 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7739. Min Act: -0.1700
Data Index: 2396120 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7739. Min Act: -0.1700
Data Index: 8311403 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7739. Min Act: -0.1700
Data Index: 8314618 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7739. Min Act: -0.1700
Data Index: 4940139 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7739. Min Act: -0.1700
Data Index: 8807234 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7114. Min Act: -0.1700
Data Index: 528199 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7114. Min Act: -0.1700
Data Index: 4767286 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7114. Min Act: -0.1700
Data Index: 6704164 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7114. Min Act: -0.1700
Data Index: 7087137 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7114. Min Act: -0.1700
Data Index: 8804257 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0239. Min Range: -8.0239
Max Act: 7.7114. Min Act: -0.1700
Data Index: 704850 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19