Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2652 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.9652. Min Act: -0.1700
Data Index: 1593636 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.8402. Min Act: -0.1700
Data Index: 7029125 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.8402. Min Act: -0.1700
Data Index: 803502 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.7465. Min Act: -0.1700
Data Index: 6590378 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.7152. Min Act: -0.1700
Data Index: 8478484 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.6840. Min Act: -0.1700
Data Index: 6787485 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.6527. Min Act: -0.1700
Data Index: 1869987 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5902. Min Act: -0.1700
Data Index: 8135448 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5902. Min Act: -0.1700
Data Index: 8230048 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5590. Min Act: -0.1700
Data Index: 7127570 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5277. Min Act: -0.1700
Data Index: 3389325 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5277. Min Act: -0.1700
Data Index: 1860807 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5277. Min Act: -0.1700
Data Index: 7627411 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5277. Min Act: -0.1700
Data Index: 7371259 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.5277. Min Act: -0.1700
Data Index: 6656643 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.4965. Min Act: -0.1700
Data Index: 8507083 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.4965. Min Act: -0.1700
Data Index: 1411420 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.4965. Min Act: -0.1700
Data Index: 4894799 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.4652. Min Act: -0.1700
Data Index: 4900645 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9652. Min Range: -6.9652
Max Act: 6.4652. Min Act: -0.1700
Data Index: 7756634 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19