Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.6742. Min Act: -0.1700
Data Index: 3873516 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.6117. Min Act: -0.1700
Data Index: 4977509 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.5492. Min Act: -0.1700
Data Index: 2183313 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.4554. Min Act: -0.1700
Data Index: 4503041 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.4554. Min Act: -0.1700
Data Index: 850251 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.4242. Min Act: -0.1700
Data Index: 11544 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.3929. Min Act: -0.1700
Data Index: 850861 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.3304. Min Act: -0.1700
Data Index: 7015578 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.3304. Min Act: -0.1700
Data Index: 6874083 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.2992. Min Act: -0.1700
Data Index: 8587923 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.2679. Min Act: -0.1700
Data Index: 721196 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.2679. Min Act: -0.1700
Data Index: 6518401 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.2367. Min Act: -0.1700
Data Index: 6219902 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.2367. Min Act: -0.1700
Data Index: 5440645 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.1742. Min Act: -0.1700
Data Index: 3567374 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.1429. Min Act: -0.1700
Data Index: 5668605 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.1429. Min Act: -0.1700
Data Index: 986613 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.1429. Min Act: -0.1700
Data Index: 5723294 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.1429. Min Act: -0.1700
Data Index: 2124479 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6742. Min Range: -7.6742
Max Act: 7.1117. Min Act: -0.1700
Data Index: 696262 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19