Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2481 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.5383. Min Act: -0.1700
Data Index: 4401531 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.5383. Min Act: -0.1700
Data Index: 6727363 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.5070. Min Act: -0.1700
Data Index: 2632559 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.4913. Min Act: -0.1700
Data Index: 6726922 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.4443. Min Act: -0.1700
Data Index: 3230438 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.4286. Min Act: -0.1700
Data Index: 8679524 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.4130. Min Act: -0.1700
Data Index: 6336457 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.4130. Min Act: -0.1700
Data Index: 5728127 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.4130. Min Act: -0.1700
Data Index: 8397907 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.4130. Min Act: -0.1700
Data Index: 242846 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3816. Min Act: -0.1700
Data Index: 185886 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3816. Min Act: -0.1700
Data Index: 1972777 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3973. Min Act: -0.1700
Data Index: 948489 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3816. Min Act: -0.1700
Data Index: 1324444 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3659. Min Act: -0.1700
Data Index: 5151135 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3502. Min Act: -0.1700
Data Index: 3820142 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3659. Min Act: -0.1700
Data Index: 1796242 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3346. Min Act: -0.1700
Data Index: 1598485 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3502. Min Act: -0.1700
Data Index: 5828287 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5383. Min Range: -3.5383
Max Act: 3.3502. Min Act: -0.1700
Data Index: 6142600 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19