Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4405 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4749276 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4627. Min Act: -0.1700
Data Index: 7700008 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.4315. Min Act: -0.1700
Data Index: 1984193 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2752. Min Act: -0.1700
Data Index: 6549566 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2440. Min Act: -0.1700
Data Index: 3632087 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2127. Min Act: -0.1700
Data Index: 8564385 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2127. Min Act: -0.1700
Data Index: 568553 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2127. Min Act: -0.1700
Data Index: 227557 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1815. Min Act: -0.1700
Data Index: 1993263 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.2127. Min Act: -0.1700
Data Index: 480137 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1815. Min Act: -0.1700
Data Index: 3662055 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1815. Min Act: -0.1700
Data Index: 1522716 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1502. Min Act: -0.1700
Data Index: 6002693 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1502. Min Act: -0.1700
Data Index: 3861689 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1815. Min Act: -0.1700
Data Index: 4997316 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1502. Min Act: -0.1700
Data Index: 6946487 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1815. Min Act: -0.1700
Data Index: 298172 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1502. Min Act: -0.1700
Data Index: 6459123 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1190. Min Act: -0.1700
Data Index: 6010817 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5877. Min Range: -5.5877
Max Act: 5.1190. Min Act: -0.1700
Data Index: 2256096 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19