Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1453 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.9709. Min Act: -0.1700
Data Index: 4158984 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.7834. Min Act: -0.1700
Data Index: 6855564 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.6272. Min Act: -0.1700
Data Index: 1649750 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.6272. Min Act: -0.1700
Data Index: 6014788 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.5334. Min Act: -0.1700
Data Index: 7547176 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.5022. Min Act: -0.1700
Data Index: 4819457 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.4397. Min Act: -0.1700
Data Index: 2558509 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.4084. Min Act: -0.1700
Data Index: 5591183 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.4084. Min Act: -0.1700
Data Index: 1753638 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.4084. Min Act: -0.1700
Data Index: 2344224 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.4084. Min Act: -0.1700
Data Index: 5654385 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.4084. Min Act: -0.1700
Data Index: 3129169 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3459. Min Act: -0.1700
Data Index: 5043610 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3772. Min Act: -0.1700
Data Index: 1356908 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3772. Min Act: -0.1700
Data Index: 6672967 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3772. Min Act: -0.1700
Data Index: 1877284 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3772. Min Act: -0.1700
Data Index: 7723415 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3147. Min Act: -0.1700
Data Index: 674744 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3147. Min Act: -0.1700
Data Index: 4161668 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9709. Min Range: -5.9709
Max Act: 5.3147. Min Act: -0.1700
Data Index: 6425392 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19