Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5530 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.6273. Min Act: -0.1700
Data Index: 8711114 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.5961. Min Act: -0.1700
Data Index: 4627098 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.5961. Min Act: -0.1700
Data Index: 4007635 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.5648. Min Act: -0.1700
Data Index: 4204629 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.5023. Min Act: -0.1700
Data Index: 6405480 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.5023. Min Act: -0.1700
Data Index: 2457639 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4711. Min Act: -0.1700
Data Index: 8112423 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4398. Min Act: -0.1700
Data Index: 3208937 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4086. Min Act: -0.1700
Data Index: 3580198 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4398. Min Act: -0.1700
Data Index: 1319397 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4398. Min Act: -0.1700
Data Index: 407904 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4398. Min Act: -0.1700
Data Index: 8185653 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4086. Min Act: -0.1700
Data Index: 8237882 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.4086. Min Act: -0.1700
Data Index: 6875821 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.3461. Min Act: -0.1700
Data Index: 1572351 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.3773. Min Act: -0.1700
Data Index: 8803920 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.3461. Min Act: -0.1700
Data Index: 2418721 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.3461. Min Act: -0.1700
Data Index: 69357 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.3773. Min Act: -0.1700
Data Index: 3868693 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6273. Min Range: -6.6273
Max Act: 6.3461. Min Act: -0.1700
Data Index: 4444382 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19