Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.8081. Min Act: -0.1700
Data Index: 6899764 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.7456. Min Act: -0.1700
Data Index: 5091548 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.6831. Min Act: -0.1700
Data Index: 1982107 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.6206. Min Act: -0.1700
Data Index: 1592076 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.4956. Min Act: -0.1700
Data Index: 361945 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.5581. Min Act: -0.1700
Data Index: 8014302 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.4956. Min Act: -0.1700
Data Index: 1570212 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.4331. Min Act: -0.1700
Data Index: 5037070 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.4331. Min Act: -0.1700
Data Index: 7246554 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.3706. Min Act: -0.1700
Data Index: 5888975 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.3081. Min Act: -0.1700
Data Index: 2113402 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.3081. Min Act: -0.1700
Data Index: 7271284 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.3081. Min Act: -0.1700
Data Index: 5723176 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1831. Min Act: -0.1700
Data Index: 1162846 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.2456. Min Act: -0.1700
Data Index: 1793544 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.3081. Min Act: -0.1700
Data Index: 4917754 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1831. Min Act: -0.1700
Data Index: 1049362 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1831. Min Act: -0.1700
Data Index: 5905732 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1831. Min Act: -0.1700
Data Index: 2104228 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8081. Min Range: -8.8081
Max Act: 8.1831. Min Act: -0.1700
Data Index: 4153541 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19