Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4458. Min Range: -6.4458
Max Act: 6.4458. Min Act: -0.1700
Data Index: 8631897 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4458. Min Range: -6.4458
Max Act: 6.4145. Min Act: -0.1700
Data Index: 7696220 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4458. Min Range: -6.4458
Max Act: 6.1333. Min Act: -0.1700
Data Index: 4923269 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4458. Min Range: -6.4458
Max Act: 6.0395. Min Act: -0.1700
Data Index: 8330296 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4458. Min Range: -6.4458
Max Act: 6.0083. Min Act: -0.1700
Data Index: 4896351 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4458. Min Range: -6.4458
Max Act: 6.0083. Min Act: -0.1700
Data Index: 4592229 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4458. Min Range: -6.4458
Max Act: 6.0395. Min Act: -0.1700
Data Index: 4522788 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.9770. Min Act: -0.1700
Data Index: 5440177 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.9770. Min Act: -0.1700
Data Index: 3735044 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.8833. Min Act: -0.1700
Data Index: 2805990 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.9145. Min Act: -0.1700
Data Index: 7372238 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.8833. Min Act: -0.1700
Data Index: 8695040 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.8833. Min Act: -0.1700
Data Index: 734033 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.8520. Min Act: -0.1700
Data Index: 5903660 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.8520. Min Act: -0.1700
Data Index: 2978418 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.8208. Min Act: -0.1700
Data Index: 4856579 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.8208. Min Act: -0.1700
Data Index: 1720161 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.7583. Min Act: -0.1700
Data Index: 5745074 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.7583. Min Act: -0.1700
Data Index: 4656904 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4458. Min Range: -6.4458
Max Act: 5.7583. Min Act: -0.1700
Data Index: 7850413 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19