Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 934 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.7646. Min Act: -0.1700
Data Index: 3888543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.7646. Min Act: -0.1700
Data Index: 4948294 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.7646. Min Act: -0.1700
Data Index: 7554022 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.7646. Min Act: -0.1700
Data Index: 8328414 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.7646. Min Act: -0.1700
Data Index: 1998251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.6396. Min Act: -0.1700
Data Index: 7148873 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.5146. Min Act: -0.1700
Data Index: 8618399 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.4834. Min Act: -0.1700
Data Index: 5313544 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.4209. Min Act: -0.1700
Data Index: 2901946 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.4209. Min Act: -0.1700
Data Index: 1281390 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.4521. Min Act: -0.1700
Data Index: 2853113 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.4209. Min Act: -0.1700
Data Index: 4544187 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.4209. Min Act: -0.1700
Data Index: 2876925 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.3896. Min Act: -0.1700
Data Index: 7688450 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.3896. Min Act: -0.1700
Data Index: 3937010 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.3584. Min Act: -0.1700
Data Index: 571954 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.3584. Min Act: -0.1700
Data Index: 4904581 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.3584. Min Act: -0.1700
Data Index: 1739296 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.3584. Min Act: -0.1700
Data Index: 2853111 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7646. Min Range: -4.7646
Max Act: 4.3271. Min Act: -0.1700
Data Index: 2637443 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19