Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 328 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.1258. Min Act: -0.1700
Data Index: 4285887 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1258. Min Range: -3.1258
Max Act: 3.0628. Min Act: -0.1700
Data Index: 5907234 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9838. Min Act: -0.1700
Data Index: 4033569 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9522. Min Act: -0.1700
Data Index: 1960205 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9046. Min Act: -0.1700
Data Index: 8235978 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.9046. Min Act: -0.1700
Data Index: 4420518 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8888. Min Act: -0.1700
Data Index: 7824513 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8888. Min Act: -0.1700
Data Index: 1662666 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8570. Min Act: -0.1700
Data Index: 3038305 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8411. Min Act: -0.1700
Data Index: 2189604 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8411. Min Act: -0.1700
Data Index: 3242389 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8411. Min Act: -0.1700
Data Index: 3622251 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8570. Min Act: -0.1700
Data Index: 4351705 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8093. Min Act: -0.1700
Data Index: 766668 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.7934. Min Act: -0.1700
Data Index: 7480759 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.7934. Min Act: -0.1700
Data Index: 1049183 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.7775. Min Act: -0.1700
Data Index: 8129603 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.8093. Min Act: -0.1700
Data Index: 3143409 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.7934. Min Act: -0.1700
Data Index: 5623694 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1258. Min Range: -3.1258
Max Act: 2.7934. Min Act: -0.1700
Data Index: 3320318 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19