Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4134 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.3236. Min Act: -0.1700
Data Index: 6521633 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.3236. Min Act: -0.1700
Data Index: 4204133 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.2611. Min Act: -0.1700
Data Index: 3252070 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.2299. Min Act: -0.1700
Data Index: 2490236 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1986. Min Act: -0.1700
Data Index: 780135 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1986. Min Act: -0.1700
Data Index: 3384872 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1674. Min Act: -0.1700
Data Index: 1043597 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1674. Min Act: -0.1700
Data Index: 3036340 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1674. Min Act: -0.1700
Data Index: 7749747 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1049. Min Act: -0.1700
Data Index: 2005732 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1049. Min Act: -0.1700
Data Index: 6521634 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1049. Min Act: -0.1700
Data Index: 2564555 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1049. Min Act: -0.1700
Data Index: 2715431 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1049. Min Act: -0.1700
Data Index: 2564550 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1049. Min Act: -0.1700
Data Index: 4006889 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.1049. Min Act: -0.1700
Data Index: 6586162 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.0736. Min Act: -0.1700
Data Index: 1330453 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.0736. Min Act: -0.1700
Data Index: 6170734 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.0736. Min Act: -0.1700
Data Index: 1004403 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3236. Min Range: -6.3236
Max Act: 6.0424. Min Act: -0.1700
Data Index: 4689332 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19