Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.7531. Min Act: -0.1700
Data Index: 3553769 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.5969. Min Act: -0.1700
Data Index: 7831534 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.5031. Min Act: -0.1700
Data Index: 7345241 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.4719. Min Act: -0.1700
Data Index: 1093926 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.3781. Min Act: -0.1700
Data Index: 3011156 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.3156. Min Act: -0.1700
Data Index: 7751797 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.2531. Min Act: -0.1700
Data Index: 4902705 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.2219. Min Act: -0.1700
Data Index: 5924368 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.2219. Min Act: -0.1700
Data Index: 7796426 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.2219. Min Act: -0.1700
Data Index: 1170357 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.2219. Min Act: -0.1700
Data Index: 5644999 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1906. Min Act: -0.1700
Data Index: 3198767 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1906. Min Act: -0.1700
Data Index: 588411 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1906. Min Act: -0.1700
Data Index: 6460948 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1594. Min Act: -0.1700
Data Index: 3011158 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1594. Min Act: -0.1700
Data Index: 1783634 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1594. Min Act: -0.1700
Data Index: 2188518 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1594. Min Act: -0.1700
Data Index: 2159549 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1281. Min Act: -0.1700
Data Index: 3900414 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7531. Min Range: -6.7531
Max Act: 6.1281. Min Act: -0.1700
Data Index: 5832151 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19