Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.9976. Min Act: -0.1700
Data Index: 2086001 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.8413. Min Act: -0.1700
Data Index: 2465098 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.7476. Min Act: -0.1700
Data Index: 8504207 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.7476. Min Act: -0.1700
Data Index: 1911611 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.7476. Min Act: -0.1700
Data Index: 1671089 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.7163. Min Act: -0.1700
Data Index: 2438684 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.6538. Min Act: -0.1700
Data Index: 7785247 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.6538. Min Act: -0.1700
Data Index: 8711033 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.6538. Min Act: -0.1700
Data Index: 4682874 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.5913. Min Act: -0.1700
Data Index: 7271174 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.5288. Min Act: -0.1700
Data Index: 1831304 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.5288. Min Act: -0.1700
Data Index: 7669762 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4976. Min Act: -0.1700
Data Index: 2191799 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4663. Min Act: -0.1700
Data Index: 6735592 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4976. Min Act: -0.1700
Data Index: 670959 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4351. Min Act: -0.1700
Data Index: 121482 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4351. Min Act: -0.1700
Data Index: 2231453 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3726. Min Act: -0.1700
Data Index: 2884987 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4038. Min Act: -0.1700
Data Index: 5130730 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4038. Min Act: -0.1700
Data Index: 3409851 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19