Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6114 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0163. Min Range: -5.0163
Max Act: 5.0163. Min Act: -0.1700
Data Index: 6548988 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9538. Min Act: -0.1700
Data Index: 154561 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9538. Min Act: -0.1700
Data Index: 2136351 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9538. Min Act: -0.1700
Data Index: 3719984 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9225. Min Act: -0.1700
Data Index: 1351598 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9225. Min Act: -0.1700
Data Index: 1748178 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8913. Min Act: -0.1700
Data Index: 4698738 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9225. Min Act: -0.1700
Data Index: 205314 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9225. Min Act: -0.1700
Data Index: 3658474 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.9225. Min Act: -0.1700
Data Index: 6116126 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8913. Min Act: -0.1700
Data Index: 7908933 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8600. Min Act: -0.1700
Data Index: 3829730 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8600. Min Act: -0.1700
Data Index: 5298453 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8288. Min Act: -0.1700
Data Index: 7203407 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8288. Min Act: -0.1700
Data Index: 4337147 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8288. Min Act: -0.1700
Data Index: 937487 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.7975. Min Act: -0.1700
Data Index: 5883264 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8288. Min Act: -0.1700
Data Index: 2266353 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.7975. Min Act: -0.1700
Data Index: 6158690 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0163. Min Range: -5.0163
Max Act: 4.8288. Min Act: -0.1700
Data Index: 7685020 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19