Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4882 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.5259. Min Act: -0.1700
Data Index: 2911389 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.4946. Min Act: -0.1700
Data Index: 2274185 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.3384. Min Act: -0.1700
Data Index: 6698211 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.3071. Min Act: -0.1700
Data Index: 3720147 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.2759. Min Act: -0.1700
Data Index: 5687252 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.2446. Min Act: -0.1700
Data Index: 5046245 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.2446. Min Act: -0.1700
Data Index: 65541 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.1821. Min Act: -0.1700
Data Index: 2508284 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.1821. Min Act: -0.1700
Data Index: 5031550 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.1821. Min Act: -0.1700
Data Index: 8013552 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.1508. Min Act: -0.1700
Data Index: 2074599 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.1196. Min Act: -0.1700
Data Index: 833121 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.1196. Min Act: -0.1700
Data Index: 1197267 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.0883. Min Act: -0.1700
Data Index: 4791287 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.0571. Min Act: -0.1700
Data Index: 8335974 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5259. Min Range: -4.5259
Max Act: 3.9946. Min Act: -0.1700
Data Index: 6853153 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.0258. Min Act: -0.1700
Data Index: 6827337 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.0258. Min Act: -0.1700
Data Index: 7286442 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.0258. Min Act: -0.1700
Data Index: 6437774 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5259. Min Range: -4.5259
Max Act: 4.0258. Min Act: -0.1700
Data Index: 6418210 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19