Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3136 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.4407. Min Act: -0.1700
Data Index: 1647693 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.3263. Min Act: -0.1700
Data Index: 1369832 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.2935. Min Act: -0.1700
Data Index: 2642590 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.2605. Min Act: -0.1700
Data Index: 6797235 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.2440. Min Act: -0.1700
Data Index: 2214878 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.2109. Min Act: -0.1695
Data Index: 5600773 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1943. Min Act: -0.1700
Data Index: 1916055 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1943. Min Act: -0.1700
Data Index: 6952923 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1776. Min Act: -0.1700
Data Index: 6887762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1776. Min Act: -0.1700
Data Index: 1579593 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1776. Min Act: -0.1699
Data Index: 1600361 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1776. Min Act: -0.1697
Data Index: 8760980 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1610. Min Act: -0.1700
Data Index: 1650026 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1610. Min Act: -0.1699
Data Index: 4516331 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1443. Min Act: -0.1700
Data Index: 1032007 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1443. Min Act: -0.1700
Data Index: 2411617 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1443. Min Act: -0.1700
Data Index: 287287 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1443. Min Act: -0.1700
Data Index: 864548 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1277. Min Act: -0.1700
Data Index: 536293 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4407. Min Range: -2.4407
Max Act: 2.1277. Min Act: -0.1692
Data Index: 364269 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19