Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3312 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.9782. Min Act: -0.1700
Data Index: 6677929 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.8845. Min Act: -0.1700
Data Index: 7858765 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.7907. Min Act: -0.1700
Data Index: 2422607 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.4157. Min Act: -0.1700
Data Index: 1117973 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.3845. Min Act: -0.1700
Data Index: 5889656 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.3220. Min Act: -0.1700
Data Index: 5061575 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.3220. Min Act: -0.1700
Data Index: 54811 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.2907. Min Act: -0.1700
Data Index: 2062390 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.2282. Min Act: -0.1700
Data Index: 4842314 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.1657. Min Act: -0.1700
Data Index: 2669245 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.0407. Min Act: -0.1700
Data Index: 1757232 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9782. Min Range: -6.9782
Max Act: 6.0407. Min Act: -0.1700
Data Index: 783675 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.9782. Min Act: -0.1700
Data Index: 3090596 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 6893415 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.9470. Min Act: -0.1700
Data Index: 746362 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 4028249 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 3903083 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 8217822 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.9157. Min Act: -0.1700
Data Index: 7840796 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9782. Min Range: -6.9782
Max Act: 5.8845. Min Act: -0.1700
Data Index: 3195202 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19