Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2738 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.8374. Min Act: -0.1700
Data Index: 4412519 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.8031. Min Act: -0.1695
Data Index: 623208 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7600. Min Act: -0.1699
Data Index: 1295254 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7514. Min Act: -0.1560
Data Index: 7335143 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7341. Min Act: -0.1697
Data Index: 7505831 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7341. Min Act: -0.1359
Data Index: 7525343 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7255. Min Act: -0.1612
Data Index: 300639 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7168. Min Act: -0.1697
Data Index: 6670811 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7081. Min Act: -0.1693
Data Index: 1456804 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7168. Min Act: -0.1696
Data Index: 1969508 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7168. Min Act: -0.1696
Data Index: 5242722 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7255. Min Act: -0.1700
Data Index: 7260821 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7081. Min Act: -0.1666
Data Index: 2286937 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.6995. Min Act: -0.1698
Data Index: 186873 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.6995. Min Act: -0.1574
Data Index: 2312504 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.7168. Min Act: -0.1688
Data Index: 967303 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.6908. Min Act: -0.1700
Data Index: 465046 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.6995. Min Act: -0.1700
Data Index: 3723541 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.6995. Min Act: -0.1555
Data Index: 4072222 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8374. Min Range: -1.8374
Max Act: 1.6995. Min Act: -0.1689
Data Index: 3033652 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19