Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1452 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.7167. Min Act: -0.1700
Data Index: 7279659 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.6542. Min Act: -0.1700
Data Index: 4212942 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.6542. Min Act: -0.1700
Data Index: 5746682 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.4667. Min Act: -0.1700
Data Index: 1186317 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.4042. Min Act: -0.1700
Data Index: 1000210 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.4354. Min Act: -0.1700
Data Index: 5988861 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.4042. Min Act: -0.1700
Data Index: 5677773 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.3417. Min Act: -0.1700
Data Index: 237228 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.3729. Min Act: -0.1700
Data Index: 4706963 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.3417. Min Act: -0.1700
Data Index: 3154397 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.3417. Min Act: -0.1700
Data Index: 1893013 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.3104. Min Act: -0.1700
Data Index: 4397499 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.3104. Min Act: -0.1700
Data Index: 3343083 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.3417. Min Act: -0.1700
Data Index: 4092397 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.2479. Min Act: -0.1700
Data Index: 3650854 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.2792. Min Act: -0.1700
Data Index: 3440254 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.2792. Min Act: -0.1700
Data Index: 7192739 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.2479. Min Act: -0.1700
Data Index: 5746089 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.2479. Min Act: -0.1700
Data Index: 2456162 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7167. Min Range: -5.7167
Max Act: 5.1854. Min Act: -0.1700
Data Index: 3092047 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19