Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.4514. Min Act: -0.1700
Data Index: 761642 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.4201. Min Act: -0.1700
Data Index: 4259041 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.3264. Min Act: -0.1700
Data Index: 7567544 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.3576. Min Act: -0.1700
Data Index: 7394443 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2951. Min Act: -0.1700
Data Index: 526889 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2951. Min Act: -0.1700
Data Index: 7596091 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2326. Min Act: -0.1700
Data Index: 5588923 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2639. Min Act: -0.1700
Data Index: 5828202 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2326. Min Act: -0.1700
Data Index: 70038 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2326. Min Act: -0.1700
Data Index: 6932414 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2014. Min Act: -0.1700
Data Index: 1051453 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.2014. Min Act: -0.1700
Data Index: 3709536 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.1389. Min Act: -0.1700
Data Index: 4074908 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.1389. Min Act: -0.1700
Data Index: 4501435 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.1389. Min Act: -0.1700
Data Index: 6365383 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.0764. Min Act: -0.1700
Data Index: 41829 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.1076. Min Act: -0.1700
Data Index: 7627645 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.1076. Min Act: -0.1700
Data Index: 8654139 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.1076. Min Act: -0.1700
Data Index: 4497958 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4514. Min Range: -6.4514
Max Act: 6.0764. Min Act: -0.1700
Data Index: 5808275 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19