Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.6213. Min Act: -0.1700
Data Index: 7039260 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.4025. Min Act: -0.1700
Data Index: 589355 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.3088. Min Act: -0.1700
Data Index: 4785566 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.2775. Min Act: -0.1700
Data Index: 6286571 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.2463. Min Act: -0.1700
Data Index: 7376353 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.2775. Min Act: -0.1700
Data Index: 1116673 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.2150. Min Act: -0.1700
Data Index: 4544351 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.2150. Min Act: -0.1700
Data Index: 1705217 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1838. Min Act: -0.1700
Data Index: 7784245 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1838. Min Act: -0.1700
Data Index: 6767882 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.2150. Min Act: -0.1700
Data Index: 6184951 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1838. Min Act: -0.1700
Data Index: 6676595 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1525. Min Act: -0.1700
Data Index: 8374678 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1525. Min Act: -0.1700
Data Index: 8189157 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1525. Min Act: -0.1700
Data Index: 7436896 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.0900. Min Act: -0.1700
Data Index: 3666447 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1213. Min Act: -0.1700
Data Index: 7757088 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1213. Min Act: -0.1700
Data Index: 5336047 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1213. Min Act: -0.1700
Data Index: 7865224 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6213. Min Range: -5.6213
Max Act: 5.1213. Min Act: -0.1700
Data Index: 7981308 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19