Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1592 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.8943. Min Act: -0.1700
Data Index: 2829389 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.6756. Min Act: -0.1700
Data Index: 5051761 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.6443. Min Act: -0.1700
Data Index: 3421908 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.6131. Min Act: -0.1700
Data Index: 1211294 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.6131. Min Act: -0.1700
Data Index: 3647248 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.5818. Min Act: -0.1700
Data Index: 6235229 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.5193. Min Act: -0.1700
Data Index: 5857462 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.4881. Min Act: -0.1700
Data Index: 5722468 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.4881. Min Act: -0.1700
Data Index: 4582907 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.4568. Min Act: -0.1700
Data Index: 2827101 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.4256. Min Act: -0.1700
Data Index: 8681240 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.4256. Min Act: -0.1700
Data Index: 8112736 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.4568. Min Act: -0.1700
Data Index: 2580430 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.4256. Min Act: -0.1700
Data Index: 3952965 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.3943. Min Act: -0.1700
Data Index: 4707162 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.3631. Min Act: -0.1700
Data Index: 8512388 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.3943. Min Act: -0.1700
Data Index: 5288801 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.3631. Min Act: -0.1700
Data Index: 1589186 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.3943. Min Act: -0.1700
Data Index: 696599 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8943. Min Range: -5.8943
Max Act: 5.3631. Min Act: -0.1700
Data Index: 2986204 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19