Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4254 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.6419. Min Act: -0.1700
Data Index: 4574750 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.4232. Min Act: -0.1700
Data Index: 5304777 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.3607. Min Act: -0.1700
Data Index: 4666632 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.3607. Min Act: -0.1700
Data Index: 7977973 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.3294. Min Act: -0.1700
Data Index: 5075354 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.3294. Min Act: -0.1700
Data Index: 7006563 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.3294. Min Act: -0.1700
Data Index: 2134782 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.2669. Min Act: -0.1700
Data Index: 5224251 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.2357. Min Act: -0.1700
Data Index: 1114103 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.2357. Min Act: -0.1700
Data Index: 5329858 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.2669. Min Act: -0.1700
Data Index: 2141968 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.2044. Min Act: -0.1700
Data Index: 956304 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.1419. Min Act: -0.1700
Data Index: 965335 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.1107. Min Act: -0.1700
Data Index: 858573 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.1419. Min Act: -0.1700
Data Index: 4216089 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.1107. Min Act: -0.1700
Data Index: 562942 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.1107. Min Act: -0.1700
Data Index: 6204248 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.0794. Min Act: -0.1700
Data Index: 3875185 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.0482. Min Act: -0.1700
Data Index: 312669 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6419. Min Range: -6.6419
Max Act: 6.0794. Min Act: -0.1700
Data Index: 2311308 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19