Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.6357. Min Act: -0.1700
Data Index: 8351003 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.6201. Min Act: -0.1700
Data Index: 5557442 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.6201. Min Act: -0.1700
Data Index: 4974283 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.5731. Min Act: -0.1700
Data Index: 1115673 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.5575. Min Act: -0.1700
Data Index: 3603531 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.5418. Min Act: -0.1700
Data Index: 7478908 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.5105. Min Act: -0.1700
Data Index: 4645089 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.4948. Min Act: -0.1700
Data Index: 4084028 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.4322. Min Act: -0.1700
Data Index: 8663844 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.3851. Min Act: -0.1700
Data Index: 380273 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.3224. Min Act: -0.1700
Data Index: 185214 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.3538. Min Act: -0.1700
Data Index: 3225270 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.3067. Min Act: -0.1700
Data Index: 5433015 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.2753. Min Act: -0.1700
Data Index: 7930767 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.2753. Min Act: -0.1700
Data Index: 6847139 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.2753. Min Act: -0.1700
Data Index: 8381298 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.2910. Min Act: -0.1700
Data Index: 2861832 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.2753. Min Act: -0.1700
Data Index: 3325530 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.2753. Min Act: -0.1700
Data Index: 7355079 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6357. Min Range: -3.6357
Max Act: 3.2439. Min Act: -0.1700
Data Index: 3931585 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19