Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3592 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1273. Min Range: -6.1273
Max Act: 6.1273. Min Act: -0.1700
Data Index: 6264644 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.6586. Min Act: -0.1700
Data Index: 1199558 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.5336. Min Act: -0.1700
Data Index: 589282 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.4711. Min Act: -0.1700
Data Index: 836329 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.5023. Min Act: -0.1700
Data Index: 3745555 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.4398. Min Act: -0.1700
Data Index: 8820773 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.4086. Min Act: -0.1700
Data Index: 8273748 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.4086. Min Act: -0.1700
Data Index: 3662731 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 4824101 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 886501 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.3773. Min Act: -0.1700
Data Index: 6181328 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.3148. Min Act: -0.1700
Data Index: 5151042 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.3148. Min Act: -0.1700
Data Index: 1410966 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.2836. Min Act: -0.1700
Data Index: 2536843 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.2836. Min Act: -0.1700
Data Index: 917538 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.2523. Min Act: -0.1700
Data Index: 7989622 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.2523. Min Act: -0.1700
Data Index: 7114537 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.2211. Min Act: -0.1700
Data Index: 1516489 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.2523. Min Act: -0.1700
Data Index: 3957494 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1273. Min Range: -6.1273
Max Act: 5.2211. Min Act: -0.1700
Data Index: 3620814 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19