Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 719 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.5845. Min Act: -0.1700
Data Index: 4653294 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.5684. Min Act: -0.1698
Data Index: 44877 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.5361. Min Act: -0.1674
Data Index: 1754944 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.5523. Min Act: -0.1700
Data Index: 6982850 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.5200. Min Act: -0.1700
Data Index: 6750426 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4876. Min Act: -0.1700
Data Index: 2550254 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.5038. Min Act: -0.1700
Data Index: 7967386 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4876. Min Act: -0.1700
Data Index: 4606444 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4388. Min Act: -0.1700
Data Index: 1475420 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4388. Min Act: -0.1700
Data Index: 4181981 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4388. Min Act: -0.1700
Data Index: 6749482 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4388. Min Act: -0.1700
Data Index: 181620 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4226. Min Act: -0.1700
Data Index: 8543995 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4226. Min Act: -0.1700
Data Index: 2335806 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4226. Min Act: -0.1700
Data Index: 194074 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4226. Min Act: -0.1700
Data Index: 4486284 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4226. Min Act: -0.1700
Data Index: 6465598 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4063. Min Act: -0.1685
Data Index: 6144385 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.4226. Min Act: -0.1700
Data Index: 7459286 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5845. Min Range: -2.5845
Max Act: 2.3899. Min Act: -0.1700
Data Index: 7120161 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19