Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4934 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.2612. Min Act: -0.1700
Data Index: 669669 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.2300. Min Act: -0.1700
Data Index: 438487 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.2300. Min Act: -0.1700
Data Index: 4072599 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.1675. Min Act: -0.1700
Data Index: 8529204 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0737. Min Act: -0.1700
Data Index: 6727955 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0737. Min Act: -0.1700
Data Index: 4810009 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0425. Min Act: -0.1700
Data Index: 4810015 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2612. Min Range: -5.2612
Max Act: 5.0112. Min Act: -0.1700
Data Index: 669676 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.9487. Min Act: -0.1700
Data Index: 438490 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.9175. Min Act: -0.1700
Data Index: 7036854 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 1101306 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.9175. Min Act: -0.1700
Data Index: 1498703 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.9487. Min Act: -0.1700
Data Index: 4406140 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.9175. Min Act: -0.1700
Data Index: 6584703 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8611476 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.8550. Min Act: -0.1700
Data Index: 669670 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.8862. Min Act: -0.1700
Data Index: 8684199 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.8550. Min Act: -0.1700
Data Index: 6134745 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.8237. Min Act: -0.1700
Data Index: 669672 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2612. Min Range: -5.2612
Max Act: 4.7925. Min Act: -0.1700
Data Index: 4406139 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19