Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1574 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0984. Min Range: -8.0984
Max Act: 8.0984. Min Act: -0.1700
Data Index: 8265591 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0984. Min Range: -8.0984
Max Act: 8.0046. Min Act: -0.1700
Data Index: 8224235 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0984. Min Range: -8.0984
Max Act: 8.0046. Min Act: -0.1700
Data Index: 2636888 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.9734. Min Act: -0.1700
Data Index: 7088761 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.8796. Min Act: -0.1700
Data Index: 3093570 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.9109. Min Act: -0.1700
Data Index: 5041516 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.8171. Min Act: -0.1700
Data Index: 1595822 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.7234. Min Act: -0.1700
Data Index: 1400987 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.6921. Min Act: -0.1700
Data Index: 4007052 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.6609. Min Act: -0.1700
Data Index: 7130820 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.6296. Min Act: -0.1700
Data Index: 7713416 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5984. Min Act: -0.1700
Data Index: 8059852 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5984. Min Act: -0.1700
Data Index: 8224236 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5359. Min Act: -0.1700
Data Index: 1831566 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5359. Min Act: -0.1700
Data Index: 7590045 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5046. Min Act: -0.1700
Data Index: 2567300 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5046. Min Act: -0.1700
Data Index: 8508458 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5046. Min Act: -0.1700
Data Index: 4809259 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.5046. Min Act: -0.1700
Data Index: 4876330 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0984. Min Range: -8.0984
Max Act: 7.4734. Min Act: -0.1700
Data Index: 5842633 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19