Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5117 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.8965. Min Act: -0.1700
Data Index: 7176541 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.8340. Min Act: -0.1700
Data Index: 857207 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.6153. Min Act: -0.1700
Data Index: 4440359 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5840. Min Act: -0.1700
Data Index: 4996594 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5528. Min Act: -0.1700
Data Index: 2341585 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.5215. Min Act: -0.1700
Data Index: 1835917 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.4903. Min Act: -0.1700
Data Index: 4180178 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.4590. Min Act: -0.1700
Data Index: 93256 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.4278. Min Act: -0.1700
Data Index: 6927593 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.3653. Min Act: -0.1700
Data Index: 1465500 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.3653. Min Act: -0.1700
Data Index: 1184842 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.3340. Min Act: -0.1700
Data Index: 8605321 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.3340. Min Act: -0.1700
Data Index: 4171091 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.3340. Min Act: -0.1700
Data Index: 3884748 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.3028. Min Act: -0.1700
Data Index: 8334726 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.2715. Min Act: -0.1700
Data Index: 8720665 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.2403. Min Act: -0.1700
Data Index: 6884481 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.2403. Min Act: -0.1700
Data Index: 6590091 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.2403. Min Act: -0.1700
Data Index: 1328634 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8965. Min Range: -6.8965
Max Act: 6.2403. Min Act: -0.1700
Data Index: 5159387 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19