Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2184 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.7410. Min Act: -0.1700
Data Index: 4008339 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.7254. Min Act: -0.1700
Data Index: 3525504 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.6628. Min Act: -0.1700
Data Index: 8421140 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.6002. Min Act: -0.1700
Data Index: 7997618 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5689. Min Act: -0.1700
Data Index: 7211100 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5533. Min Act: -0.1700
Data Index: 967884 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5533. Min Act: -0.1700
Data Index: 1982072 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5219. Min Act: -0.1700
Data Index: 4423543 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5063. Min Act: -0.1700
Data Index: 5798627 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5219. Min Act: -0.1700
Data Index: 1300233 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.4906. Min Act: -0.1700
Data Index: 6325075 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.4906. Min Act: -0.1700
Data Index: 3667454 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5063. Min Act: -0.1700
Data Index: 3194426 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5063. Min Act: -0.1700
Data Index: 5777294 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.4906. Min Act: -0.1700
Data Index: 336286 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.4593. Min Act: -0.1700
Data Index: 2524119 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.5063. Min Act: -0.1700
Data Index: 831319 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.4436. Min Act: -0.1700
Data Index: 4602489 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.4593. Min Act: -0.1700
Data Index: 5287017 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7410. Min Range: -3.7410
Max Act: 3.4750. Min Act: -0.1700
Data Index: 4734751 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19