Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4742 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.5374. Min Act: -0.1700
Data Index: 1725174 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.4749. Min Act: -0.1700
Data Index: 6131168 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.2874. Min Act: -0.1700
Data Index: 369692 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.1624. Min Act: -0.1700
Data Index: 5210284 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.1624. Min Act: -0.1700
Data Index: 2388192 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.1624. Min Act: -0.1700
Data Index: 2771185 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.0999. Min Act: -0.1700
Data Index: 8747282 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5374. Min Range: -12.5374
Max Act: 12.0374. Min Act: -0.1700
Data Index: 1799353 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.9749. Min Act: -0.1700
Data Index: 8045764 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.9124. Min Act: -0.1700
Data Index: 7360928 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.9749. Min Act: -0.1700
Data Index: 3928462 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.9124. Min Act: -0.1700
Data Index: 6096207 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.8499. Min Act: -0.1700
Data Index: 1799354 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.8499. Min Act: -0.1700
Data Index: 2906372 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.9124. Min Act: -0.1700
Data Index: 884105 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.8499. Min Act: -0.1700
Data Index: 4849662 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.7874. Min Act: -0.1700
Data Index: 2820845 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.7874. Min Act: -0.1700
Data Index: 3752040 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.7874. Min Act: -0.1700
Data Index: 5240015 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5374. Min Range: -12.5374
Max Act: 11.7249. Min Act: -0.1700
Data Index: 8301373 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19