Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5579 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.9904. Min Act: -0.1700
Data Index: 7245728 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.9591. Min Act: -0.1700
Data Index: 3387727 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.9279. Min Act: -0.1700
Data Index: 1567513 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.9279. Min Act: -0.1700
Data Index: 2244478 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.9279. Min Act: -0.1700
Data Index: 3814113 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.8654. Min Act: -0.1700
Data Index: 4503717 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.8341. Min Act: -0.1700
Data Index: 6763723 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.8029. Min Act: -0.1700
Data Index: 5130358 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.8029. Min Act: -0.1700
Data Index: 3776383 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.7404. Min Act: -0.1700
Data Index: 3468207 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.7404. Min Act: -0.1700
Data Index: 4357548 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.7091. Min Act: -0.1700
Data Index: 7933253 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.7091. Min Act: -0.1700
Data Index: 8649634 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.7091. Min Act: -0.1700
Data Index: 1351637 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.7091. Min Act: -0.1700
Data Index: 3480873 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.6779. Min Act: -0.1700
Data Index: 1620344 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.6466. Min Act: -0.1700
Data Index: 2495384 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.6466. Min Act: -0.1700
Data Index: 559157 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.6154. Min Act: -0.1700
Data Index: 3988516 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9904. Min Range: -5.9904
Max Act: 5.6466. Min Act: -0.1700
Data Index: 6221805 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19