Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 308 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5306. Min Range: -8.5306
Max Act: 8.5306. Min Act: -0.1700
Data Index: 4925284 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5306. Min Range: -8.5306
Max Act: 8.4681. Min Act: -0.1700
Data Index: 3250278 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5306. Min Range: -8.5306
Max Act: 8.1556. Min Act: -0.1700
Data Index: 365462 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5306. Min Range: -8.5306
Max Act: 8.0306. Min Act: -0.1700
Data Index: 5555115 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9994. Min Act: -0.1700
Data Index: 7229257 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9994. Min Act: -0.1700
Data Index: 1891296 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9369. Min Act: -0.1700
Data Index: 5554428 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9369. Min Act: -0.1700
Data Index: 2556702 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9369. Min Act: -0.1700
Data Index: 1346477 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9056. Min Act: -0.1700
Data Index: 4670172 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9056. Min Act: -0.1700
Data Index: 5343906 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9056. Min Act: -0.1700
Data Index: 40029 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9056. Min Act: -0.1700
Data Index: 3929683 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.9056. Min Act: -0.1700
Data Index: 3389442 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.8744. Min Act: -0.1700
Data Index: 267398 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.8744. Min Act: -0.1700
Data Index: 2952402 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.8744. Min Act: -0.1700
Data Index: 4726375 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.8744. Min Act: -0.1700
Data Index: 348327 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.8431. Min Act: -0.1700
Data Index: 1612244 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5306. Min Range: -8.5306
Max Act: 7.8431. Min Act: -0.1700
Data Index: 6640708 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19