Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3270. Min Range: -7.3270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 3073597 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3270. Min Range: -7.3270
Max Act: 7.0458. Min Act: -0.1700
Data Index: 1937189 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.9520. Min Act: -0.1700
Data Index: 6351337 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.9833. Min Act: -0.1700
Data Index: 3993103 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.9520. Min Act: -0.1700
Data Index: 8149298 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8895. Min Act: -0.1700
Data Index: 4284010 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8270. Min Act: -0.1700
Data Index: 7061416 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8583. Min Act: -0.1700
Data Index: 5911378 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8270. Min Act: -0.1700
Data Index: 3721488 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.7958. Min Act: -0.1700
Data Index: 4286260 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8270. Min Act: -0.1700
Data Index: 3340178 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8583. Min Act: -0.1700
Data Index: 8796588 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8270. Min Act: -0.1700
Data Index: 1585564 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.7958. Min Act: -0.1700
Data Index: 3066660 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.7958. Min Act: -0.1700
Data Index: 7061418 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.7958. Min Act: -0.1700
Data Index: 6282189 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.7958. Min Act: -0.1700
Data Index: 1249038 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.7958. Min Act: -0.1700
Data Index: 6707443 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.7958. Min Act: -0.1700
Data Index: 4012986 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3270. Min Range: -7.3270
Max Act: 6.8270. Min Act: -0.1700
Data Index: 6732450 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19