Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4626 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.5039. Min Act: -0.1700
Data Index: 4920853 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.4726. Min Act: -0.1700
Data Index: 4719173 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.3476. Min Act: -0.1700
Data Index: 7559411 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.3164. Min Act: -0.1700
Data Index: 8055095 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.2851. Min Act: -0.1700
Data Index: 54711 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.2851. Min Act: -0.1700
Data Index: 1282745 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.2539. Min Act: -0.1700
Data Index: 3223013 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.2226. Min Act: -0.1700
Data Index: 892904 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1914. Min Act: -0.1700
Data Index: 7921425 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.2226. Min Act: -0.1700
Data Index: 1935042 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.2226. Min Act: -0.1700
Data Index: 7067686 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.2226. Min Act: -0.1700
Data Index: 1046090 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1914. Min Act: -0.1700
Data Index: 1826703 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1601. Min Act: -0.1700
Data Index: 3426436 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1601. Min Act: -0.1700
Data Index: 7190134 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1601. Min Act: -0.1700
Data Index: 5651190 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4958817 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1601. Min Act: -0.1700
Data Index: 4201654 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1601. Min Act: -0.1700
Data Index: 2729299 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5039. Min Range: -6.5039
Max Act: 6.1289. Min Act: -0.1700
Data Index: 4029818 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19